ai Trend Report
Dashboard へ戻る
0
High impact
0
Mid impact
400
Signal watch
なぜこのサイトを作ったのか
私たちそれぞれが個別にAIを使って情報収集し、同じような3行要約を作るたびに、世界中で膨大な電力と計算リソースが消費されています。 本プロジェクトは、あらかじめ広範な情報を取得・集約しておくことで、個別のAI実行回数を減らし、地球環境（GPU/TPU負荷）に配慮した効率的な情報収集を目指す実験的なダッシュボードです。
Hugging Face Papers
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
Hugging Face Papers
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
Hugging Face Papers
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
Hugging Face Papers
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
Hugging Face Papers
GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation
GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation
Hugging Face Papers
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
Hugging Face Papers
EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots
EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots
Hugging Face Papers
Wan-Streamer v0.2: Higher Resolution, Same Latency
Wan-Streamer v0.2: Higher Resolution, Same Latency
Hugging Face Papers
InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization
InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization
Hugging Face Papers
Vision Pretraining for Dense Spatial Perception
Vision Pretraining for Dense Spatial Perception
Hugging Face Papers
dOPSD: On-Policy Self-Distillation for Diffusion Language Models
dOPSD: On-Policy Self-Distillation for Diffusion Language Models
Hugging Face Papers
Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval
Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval
Hugging Face Papers
Perceptual Flow Matching for Few-Step Generative Modeling
Perceptual Flow Matching for Few-Step Generative Modeling
Hugging Face Papers
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Hugging Face Papers
LLM-as-a-Verifier: A General-Purpose Verification Framework
LLM-as-a-Verifier: A General-Purpose Verification Framework
Hugging Face Papers
Multiplayer Interactive World Models with Representation Autoencoders
Multiplayer Interactive World Models with Representation Autoencoders
Hugging Face Papers
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
Hugging Face Papers
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction
Hugging Face Papers
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
Hugging Face Papers
Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models
Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models
Hugging Face Papers
CONFLUX: A Latent Diusion Model for 3D Chest-CT Synthesis with RL Post-Training
CONFLUX: A Latent Diusion Model for 3D Chest-CT Synthesis with RL Post-Training
Hugging Face Papers
GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving
GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving
Hugging Face Papers
Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
Hugging Face Papers
PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation
PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation
機械学習タグが付けられた新着記事 - Qiita
金融データサイエンス基礎Part 6. 予測を超えて介入へ：因果推論と実験
金融データサイエンス基礎Part 6. 予測を超えて介入へ：因果推論と実験
LLMタグが付けられた新着記事 - Qiita
AIエージェントのモデルを固定しない。ai& Inferenceで考える係と作業する係をルーティングする
AIエージェントのモデルを固定しない。ai& Inferenceで考える係と作業する係をルーティングする
#AIタグ
AIの役員会で、議長が3つの反論に負けて結論を変えた——「反対専門のAI」を1体入れた審議の実録
AIの役員会で、議長が3つの反論に負けて結論を変えた——「反対専門のAI」を1体入れた審議の実録
#AIタグ
AI収益エージェント完全ガイド｜収益モデル30種類・AIエージェント50種類を体系化【2026年版】
AI収益エージェント完全ガイド｜収益モデル30種類・AIエージェント50種類を体系化【2026年版】
#AIタグ
【AI規制最前線】EU AI法の主要義務が2026年8月2日に本格適用 日本企業も対応を迫られる
【AI規制最前線】EU AI法の主要義務が2026年8月2日に本格適用 日本企業も対応を迫られる
#AIタグ
Claudeの頭の中に「心の作業机」が見つかった——AIと暮らす私が、Anthropicの新研究を読んで
Claudeの頭の中に「心の作業机」が見つかった——AIと暮らす私が、Anthropicの新研究を読んで
#AIタグ
The hybrid clinic model: Managing tele-consultations and physical walk-ins via a single clinic software
The hybrid clinic model: Managing tele-consultations and physical walk-ins via a single clinic software
ITmedia NEWS 最新記事一覧
破産の全東信、加盟店向けに競合・STORESが特別窓口 決済端末を無償提供 7月末まで
破産の全東信、加盟店向けに競合・STORESが特別窓口 決済端末を無償提供 7月末まで
ITmedia NEWS 最新記事一覧
観測史上最古の巨大ブラックホール発見 宇宙誕生から6億7000万年ごろの天体 日本のすばる望遠鏡も貢献
観測史上最古の巨大ブラックホール発見 宇宙誕生から6億7000万年ごろの天体 日本のすばる望遠鏡も貢献
ITmedia NEWS 最新記事一覧
全東信、破産を招いた「2つの事件」 カード決済の”駆け込み寺”消滅が飲食店に与える影響とは
全東信、破産を招いた「2つの事件」 カード決済の”駆け込み寺”消滅が飲食店に与える影響とは
LLMタグが付けられた新着記事 - Qiita
【RAG性能向上】ドキュメントのチャンキング（Chunking）最適化手法をコード付きで解説
【RAG性能向上】ドキュメントのチャンキング（Chunking）最適化手法をコード付きで解説
NVIDIA Blog
NVIDIA and Hugging Face Bring New Models and Frameworks to LeRobot for the Open Robotics Community
NVIDIA and Hugging Face Bring New Models and Frameworks to LeRobot for the Open Robotics Community
MarkTechPost
Tencent Releases Hy3: An Open 295B Mixture-of-Experts (MoE) Model with 21B Active Parameters and 256K Context
Tencent Releases Hy3: An Open 295B Mixture-of-Experts (MoE) Model with 21B Active Parameters and 256K Context
#LLMタグ
Amazonに学ぶ生成AIビジネス再発明！LLMを単体で使わず、検証AIやSLMを適材適所で組み合わせた最強のワークフローシステム設計術とコスト最適化の極意
Amazonに学ぶ生成AIビジネス再発明！LLMを単体で使わず、検証AIやSLMを適材適所で組み合わせた最強のワークフローシステム設計術とコスト最適化の極意
ITmedia NEWS 最新記事一覧
スターバックス、12～24歳限定の新サービス開始 公式アプリ経由で毎月100円オフの「U24パス」配布
スターバックス、12～24歳限定の新サービス開始 公式アプリ経由で毎月100円オフの「U24パス」配布
機械学習タグが付けられた新着記事 - Qiita
YAMNet TFLite で環境音をタグ付けする――ESC-50 全 2,000 本で検証
YAMNet TFLite で環境音をタグ付けする――ESC-50 全 2,000 本で検証
ITmedia NEWS 最新記事一覧
「全東信の端末使用を即時停止して」――食団連が飲食店へ注意喚起 全東信の破産受け
「全東信の端末使用を即時停止して」――食団連が飲食店へ注意喚起 全東信の破産受け
WIRED
Office Depot Coupons: Save With Promo Codes in July 2026
Office Depot Coupons: Save With Promo Codes in July 2026
WIRED
Nomad Goods Promo Codes: Get 25% Off in July 2026
Nomad Goods Promo Codes: Get 25% Off in July 2026
WIRED
Lovehoney Coupon Offers: Toys, Lingerie, and Gift Set Discounts
Lovehoney Coupon Offers: Toys, Lingerie, and Gift Set Discounts
MarkTechPost
OpenAI Releases GPT-Realtime-2.1 and GPT-Realtime-2.1-mini for Low-Latency Voice Agents in the API
OpenAI Releases GPT-Realtime-2.1 and GPT-Realtime-2.1-mini for Low-Latency Voice Agents in the API
#LLMタグ
AIへの「お願い」を「業務フロー」に変える｜Claude Code公式のループ4分類を、自分の仕事に落として解説する
AIへの「お願い」を「業務フロー」に変える｜Claude Code公式のループ4分類を、自分の仕事に落として解説する
cs.LG updates on arXiv.org
Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits
Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits
cs.LG updates on arXiv.org
Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence
Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence
cs.LG updates on arXiv.org
QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting
QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting
cs.LG updates on arXiv.org
GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech
GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech
cs.LG updates on arXiv.org
Federated Learning for Object Detection: Enabling Collaborative Drone Learning Without Centralizing Data
Federated Learning for Object Detection: Enabling Collaborative Drone Learning Without Centralizing Data
cs.LG updates on arXiv.org
Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting
Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting
cs.LG updates on arXiv.org
A Granularity-Aware EEG Feature Framework for Psychopathology Dimension Prediction
A Granularity-Aware EEG Feature Framework for Psychopathology Dimension Prediction
cs.LG updates on arXiv.org
LiNO: Lifting based multiresolution neural operator
LiNO: Lifting based multiresolution neural operator
cs.LG updates on arXiv.org
Weighted Conformal Prediction for Lab-to-Track Thermal Transfer in EV Motorsport Powertrains
Weighted Conformal Prediction for Lab-to-Track Thermal Transfer in EV Motorsport Powertrains
cs.LG updates on arXiv.org
Out-of-Distribution Generalization of Risk Aversion in Language Models
Out-of-Distribution Generalization of Risk Aversion in Language Models
cs.LG updates on arXiv.org
Safe Inference-Time Alignment via Lagrangian Reward Augmentation
Safe Inference-Time Alignment via Lagrangian Reward Augmentation
cs.LG updates on arXiv.org
Training Hybrid Block Diffusion Language Models with Partial Bidirectionality
Training Hybrid Block Diffusion Language Models with Partial Bidirectionality
cs.LG updates on arXiv.org
Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction
Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction
cs.LG updates on arXiv.org
On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization
On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization
cs.LG updates on arXiv.org
Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data
Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data
cs.LG updates on arXiv.org
Trading Confidence: Comprehensive Uncertainty Estimation in Algorithmic Trading
Trading Confidence: Comprehensive Uncertainty Estimation in Algorithmic Trading
cs.LG updates on arXiv.org
Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models
Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models
cs.LG updates on arXiv.org
Poisson-Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs
Poisson-Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs
cs.LG updates on arXiv.org
Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions
Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions
cs.LG updates on arXiv.org
Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models
Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models
cs.LG updates on arXiv.org
Bootstrap Flow-Map Tree Sampling Enables Online Feedback Driven Search
Bootstrap Flow-Map Tree Sampling Enables Online Feedback Driven Search
cs.LG updates on arXiv.org
CoFEND: A Cross-Modal Fusion End-to-End Network for Cold-Start Drug-Drug Interaction Prediction
CoFEND: A Cross-Modal Fusion End-to-End Network for Cold-Start Drug-Drug Interaction Prediction
cs.LG updates on arXiv.org
In-span learning: adapting reduced-order models using their own predictions
In-span learning: adapting reduced-order models using their own predictions
cs.LG updates on arXiv.org
Missingness as Signal: Channel-Independent Spectrogram Learning for Clinical Time Series Prediction
Missingness as Signal: Channel-Independent Spectrogram Learning for Clinical Time Series Prediction
cs.LG updates on arXiv.org
A Precedent-Guided Co-Scientist for Side-Effect-Aware Drug Redesign
A Precedent-Guided Co-Scientist for Side-Effect-Aware Drug Redesign
cs.LG updates on arXiv.org
Individual Parameters in Weight-Sparse Transformers Appear Interpretable
Individual Parameters in Weight-Sparse Transformers Appear Interpretable
cs.LG updates on arXiv.org
Rank-Order N-of-M Codes for Sparse Distributed Memory: Disentangling Representation and Learning Effects in Noise Robustness Against Contemporary Neuromorphic Architectures
Rank-Order N-of-M Codes for Sparse Distributed Memory: Disentangling Representation and Learning Effects in Noise Robustness Against Contemporary Neuromorphic Architectures
cs.LG updates on arXiv.org
MABLE: Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning
MABLE: Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning
cs.LG updates on arXiv.org
Transfer Learning in High-dimensional Ising Models
Transfer Learning in High-dimensional Ising Models
cs.LG updates on arXiv.org
Back to Basics: Improving Molecular Understanding in LLMs via SMILES-Graph Translation
Back to Basics: Improving Molecular Understanding in LLMs via SMILES-Graph Translation
cs.LG updates on arXiv.org
Do ECG Foundation Models Transfer to Rare Cardiac Diseases? Evidence from Brugada Syndrome Detection
Do ECG Foundation Models Transfer to Rare Cardiac Diseases? Evidence from Brugada Syndrome Detection
cs.LG updates on arXiv.org
Can Model Merging Improve Aggregation in DiLoCo?
Can Model Merging Improve Aggregation in DiLoCo?
cs.LG updates on arXiv.org
Out-of-distribution Neural Inference in Dynamical Ising Models
Out-of-distribution Neural Inference in Dynamical Ising Models
cs.LG updates on arXiv.org
OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models
OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models
cs.LG updates on arXiv.org
SHiPPO: Recurrent Memory with Transported Polynomial Projections
SHiPPO: Recurrent Memory with Transported Polynomial Projections
cs.LG updates on arXiv.org
LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression
LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression
cs.LG updates on arXiv.org
Spectral Rewiring for Exploration, Purification, and Model Merging
Spectral Rewiring for Exploration, Purification, and Model Merging
cs.LG updates on arXiv.org
Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification
Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification
cs.LG updates on arXiv.org
STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition
STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition
cs.LG updates on arXiv.org
Stacked LoRA for Subject-Adaptive EEG Foundation Models in Motor Imagery Decoding
Stacked LoRA for Subject-Adaptive EEG Foundation Models in Motor Imagery Decoding
cs.LG updates on arXiv.org
Heterogeneous Graph Condensation via Role-Aware Clustering
Heterogeneous Graph Condensation via Role-Aware Clustering
cs.LG updates on arXiv.org
Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights
Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights
cs.LG updates on arXiv.org
Integrating Physics-Informed Neural Networks for Safe Reinforcement Learning in a 1-DoF Helicopter System
Integrating Physics-Informed Neural Networks for Safe Reinforcement Learning in a 1-DoF Helicopter System
cs.LG updates on arXiv.org
ACPO: Adaptive Credit Policy Optimization via Fine-Grained Surrogate Entropy
ACPO: Adaptive Credit Policy Optimization via Fine-Grained Surrogate Entropy
cs.LG updates on arXiv.org
Anticipatory Reinforcement Learning for Trajectory Tracking
Anticipatory Reinforcement Learning for Trajectory Tracking
cs.LG updates on arXiv.org
Sample-Efficient Pareto Front Modeling for Energy-Aware Reinforcement Learning Using Bayesian Optimization
Sample-Efficient Pareto Front Modeling for Energy-Aware Reinforcement Learning Using Bayesian Optimization
cs.LG updates on arXiv.org
CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification
CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification
cs.LG updates on arXiv.org
Rethinking Neural Nonlinearity as Gating
Rethinking Neural Nonlinearity as Gating
cs.LG updates on arXiv.org
Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneities
Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneities
cs.LG updates on arXiv.org
Understanding electricity consumption behaviour through Inverse Reinforcement Learning
Understanding electricity consumption behaviour through Inverse Reinforcement Learning
cs.LG updates on arXiv.org
A Bayesian Framework for Evaluating Scenario Compatibility in Generative Population Synthesis
A Bayesian Framework for Evaluating Scenario Compatibility in Generative Population Synthesis
cs.LG updates on arXiv.org
Reduced-Order Models: The Mother of World Models
Reduced-Order Models: The Mother of World Models
cs.LG updates on arXiv.org
OpFlow: Learning Opportunity-Conditioned Choice Potentials for Robust OD Flow Prediction
OpFlow: Learning Opportunity-Conditioned Choice Potentials for Robust OD Flow Prediction
cs.LG updates on arXiv.org
Transition Information Density: Morphological Trajectories, Synesthetic Perception, and Structured Interpolation in Neural Training (or: The Synesthetic AI)
Transition Information Density: Morphological Trajectories, Synesthetic Perception, and Structured Interpolation in Neural Training (or: The Synesthetic AI)
cs.LG updates on arXiv.org
Joint distribution of upstream runoff governs downstream river-discharge prediction uncertainty in distributed ML models
Joint distribution of upstream runoff governs downstream river-discharge prediction uncertainty in distributed ML models
cs.LG updates on arXiv.org
PhenoNEST: A Neuro-Symbolic Framework for Ontology-Aware Multimodal Plant Phenotyping and Trait Discovery
PhenoNEST: A Neuro-Symbolic Framework for Ontology-Aware Multimodal Plant Phenotyping and Trait Discovery
cs.LG updates on arXiv.org
Unbiased Alignment for Large Language Models with Noisy Preferences
Unbiased Alignment for Large Language Models with Noisy Preferences
cs.LG updates on arXiv.org
From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model
From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model
cs.LG updates on arXiv.org
A harmonised dataset for Earth system foundation models
A harmonised dataset for Earth system foundation models
cs.LG updates on arXiv.org
Statistically Meaningful Geometry (SMG) Beyond the Euclidean Paradigm, with Application to Generative AI
Statistically Meaningful Geometry (SMG) Beyond the Euclidean Paradigm, with Application to Generative AI
cs.LG updates on arXiv.org
FedAvg for HAR: Exploring the Tradeoff Between Personalized and Generalization Accuracy
FedAvg for HAR: Exploring the Tradeoff Between Personalized and Generalization Accuracy
cs.LG updates on arXiv.org
CSympNet-ID: conformal-symplectic map learning for linearly damped Hamiltonian systems
CSympNet-ID: conformal-symplectic map learning for linearly damped Hamiltonian systems
cs.LG updates on arXiv.org
The Multiscale Single-Index Model: A Stylized Model for Hierarchical Feature Learning
The Multiscale Single-Index Model: A Stylized Model for Hierarchical Feature Learning
cs.LG updates on arXiv.org
PedestrianDiffusion: Multimodal Generative Denoising and Dense State Estimation for Inertial Navigation
PedestrianDiffusion: Multimodal Generative Denoising and Dense State Estimation for Inertial Navigation
cs.LG updates on arXiv.org
Amortising Bayesian Experimental Design for Sequential Information Gathering in LLMs
Amortising Bayesian Experimental Design for Sequential Information Gathering in LLMs
cs.LG updates on arXiv.org
How Much of the Routing Gap Is Real? Decomposing the Router-to-Oracle Gap into Reproducible Specialist Advantage and Single-Draw Label Noise
How Much of the Routing Gap Is Real? Decomposing the Router-to-Oracle Gap into Reproducible Specialist Advantage and Single-Draw Label Noise
cs.LG updates on arXiv.org
No Time Like the Present: Agentic Test-Time Training for LLM Agents
No Time Like the Present: Agentic Test-Time Training for LLM Agents
cs.LG updates on arXiv.org
Best-of-Better-$N$: Generating Pre-Aligned Responses with In-Context Learning
Best-of-Better-$N$: Generating Pre-Aligned Responses with In-Context Learning
cs.LG updates on arXiv.org
Towards Diverse and Comprehensive Benchmarks for Mutual Information Estimation
Towards Diverse and Comprehensive Benchmarks for Mutual Information Estimation
cs.LG updates on arXiv.org
A Near-Linear-Time Solver for Graph $p$-Laplacian Semi-Supervised Learning via Continuation in $p$
A Near-Linear-Time Solver for Graph $p$-Laplacian Semi-Supervised Learning via Continuation in $p$
cs.LG updates on arXiv.org
Mixture-of-Gaussians-Guided Schedule Design for Brownian Bridge Diffusion Models
Mixture-of-Gaussians-Guided Schedule Design for Brownian Bridge Diffusion Models
cs.LG updates on arXiv.org
On the Convergence of Adam, Revisited
On the Convergence of Adam, Revisited
cs.LG updates on arXiv.org
Co-Adaptive Multi-Task LoRA: Transfer-Aware, Label-Free Control of Domain Participation
Co-Adaptive Multi-Task LoRA: Transfer-Aware, Label-Free Control of Domain Participation
cs.LG updates on arXiv.org
Aligning Language Models with Selective Prediction
Aligning Language Models with Selective Prediction
cs.LG updates on arXiv.org
WeightCLIP: Aligning Datasets and Models for Weight Space Learning
WeightCLIP: Aligning Datasets and Models for Weight Space Learning
cs.LG updates on arXiv.org
Teacher Supervision over Representation Equivalence Classes
Teacher Supervision over Representation Equivalence Classes
cs.LG updates on arXiv.org
Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning
Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning
cs.LG updates on arXiv.org
When Geometry Aligns: Dihedral Hidden-State Transformations in UNet, ViT, and DiT Architectures
When Geometry Aligns: Dihedral Hidden-State Transformations in UNet, ViT, and DiT Architectures
cs.LG updates on arXiv.org
Modular Foundation Models for Time-Series Perception in Digital Twins
Modular Foundation Models for Time-Series Perception in Digital Twins
cs.LG updates on arXiv.org
Graph Classification via Network Usable Information: From Representation Evaluation to Structure Selection
Graph Classification via Network Usable Information: From Representation Evaluation to Structure Selection
cs.LG updates on arXiv.org
Implicit Bias of SGD in Multivariate ReLU Networks: Effective Width Collapse
Implicit Bias of SGD in Multivariate ReLU Networks: Effective Width Collapse
cs.LG updates on arXiv.org
Reflected Schr\"odinger Bridge Matching
Reflected Schr\"odinger Bridge Matching
cs.LG updates on arXiv.org
LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs
LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs
cs.LG updates on arXiv.org
Phase-Preserving Trimodal Transformer for Tropical Forest Biomass Estimation Using Optical and PolInSAR Data
Phase-Preserving Trimodal Transformer for Tropical Forest Biomass Estimation Using Optical and PolInSAR Data
cs.LG updates on arXiv.org
A Structural Interpretation of GELU and Threshold-Transmission Activations via the First-Order Loss Function
A Structural Interpretation of GELU and Threshold-Transmission Activations via the First-Order Loss Function
cs.LG updates on arXiv.org
Validation-Induced Shapley Shifts: How Validation Structure Distorts Data Valuation
Validation-Induced Shapley Shifts: How Validation Structure Distorts Data Valuation
cs.LG updates on arXiv.org
Rethinking AI-Generated Text Detection: A Strong Baseline and the Distribution-Shift Problem That Remains
Rethinking AI-Generated Text Detection: A Strong Baseline and the Distribution-Shift Problem That Remains
cs.LG updates on arXiv.org
PIEFS: Physics-Informed Eigenfunction Features with Learnable Scaling
PIEFS: Physics-Informed Eigenfunction Features with Learnable Scaling
cs.LG updates on arXiv.org
SAVER: Stochastic Adaptive Variance-Driven Exploration and Reconstruction for Low-Dose Computed Tomography
SAVER: Stochastic Adaptive Variance-Driven Exploration and Reconstruction for Low-Dose Computed Tomography
cs.LG updates on arXiv.org
FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity
FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity
cs.LG updates on arXiv.org
Conservative Subject Invariant EMG-based Gesture Recognition
Conservative Subject Invariant EMG-based Gesture Recognition
cs.LG updates on arXiv.org
Tensor-Train Joint Modeling for Few-Step Discrete Diffusion
Tensor-Train Joint Modeling for Few-Step Discrete Diffusion
cs.LG updates on arXiv.org
Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks
Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks
cs.LG updates on arXiv.org
Punching Above Their Weight: Classification-Head Fine-Tuning of Tiny Language Models (TLMs) for Verifiable Multiple-Choice Tasks
Punching Above Their Weight: Classification-Head Fine-Tuning of Tiny Language Models (TLMs) for Verifiable Multiple-Choice Tasks
cs.LG updates on arXiv.org
Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average
Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average
cs.LG updates on arXiv.org
Adversarial LassoNet: Robust Feature Selection via Stability-Driven Sparse Learning
Adversarial LassoNet: Robust Feature Selection via Stability-Driven Sparse Learning
cs.LG updates on arXiv.org
NeSy-CSA: A Neuro-Symbolic Framework for Open-Ended Critical Scenario Attribution
NeSy-CSA: A Neuro-Symbolic Framework for Open-Ended Critical Scenario Attribution
cs.LG updates on arXiv.org
A Unified Framework for Quantized and Continuous Strong Lottery Tickets
A Unified Framework for Quantized and Continuous Strong Lottery Tickets
cs.LG updates on arXiv.org
A Gradient Flow Perspective on Minimum MMD Estimation
A Gradient Flow Perspective on Minimum MMD Estimation
cs.LG updates on arXiv.org
AdaptiveSD A Stability-Aware, Runtime-Adaptive Speculative Decoding Framework with Multi-Policy Orchestration for CPU-Constrained LLM Inference
AdaptiveSD A Stability-Aware, Runtime-Adaptive Speculative Decoding Framework with Multi-Policy Orchestration for CPU-Constrained LLM Inference
cs.LG updates on arXiv.org
CDCP: Conditional Diffusion Model with Contextual Prompts for Multi-task Offline Safe Reinforcement Learning
CDCP: Conditional Diffusion Model with Contextual Prompts for Multi-task Offline Safe Reinforcement Learning
cs.LG updates on arXiv.org
Transformers with Physics-Informed Encodings and Simulation-Based Inference for Robust Detection of Eccentric Binary Black Holes in Pulsar Timing Array Data
Transformers with Physics-Informed Encodings and Simulation-Based Inference for Robust Detection of Eccentric Binary Black Holes in Pulsar Timing Array Data
cs.LG updates on arXiv.org
NeuroOnline: Bridging Pretraining and Online Adaptation for EEG Foundation Models
NeuroOnline: Bridging Pretraining and Online Adaptation for EEG Foundation Models
cs.LG updates on arXiv.org
MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs
MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs
cs.LG updates on arXiv.org
Order-based Causal Discovery for Multistage Processes
Order-based Causal Discovery for Multistage Processes
cs.LG updates on arXiv.org
MANCE: Manifold Aware Concept Erasure
MANCE: Manifold Aware Concept Erasure
cs.LG updates on arXiv.org
Knowing When to Stop: Predicting Execution-Consistency Convergence in Text-to-SQL
Knowing When to Stop: Predicting Execution-Consistency Convergence in Text-to-SQL
cs.LG updates on arXiv.org
Directional Curvature from Armijo Backtracking: A Low-Cost Sharpness Probe and a Calibration-Free Learning-Rate Safeguard for Adam
Directional Curvature from Armijo Backtracking: A Low-Cost Sharpness Probe and a Calibration-Free Learning-Rate Safeguard for Adam
cs.LG updates on arXiv.org
When Does Small Data Work? Accuracy and Efficiency Trade-offs Between Tabular Foundation Models and Conventional Methods for Crowd-State Classification at Hajj and Umrah
When Does Small Data Work? Accuracy and Efficiency Trade-offs Between Tabular Foundation Models and Conventional Methods for Crowd-State Classification at Hajj and Umrah
cs.LG updates on arXiv.org
A Unified Algebraic Framework for Classification Performance Evaluation
A Unified Algebraic Framework for Classification Performance Evaluation
cs.LG updates on arXiv.org
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
cs.LG updates on arXiv.org
A Unified Framework for In-Context Learning with Causal and Masked Language Models
A Unified Framework for In-Context Learning with Causal and Masked Language Models
cs.LG updates on arXiv.org
FedSPM: Routing-Enabled Federated Learning under Dual Heterogeneity via Semiparametric Mixture
FedSPM: Routing-Enabled Federated Learning under Dual Heterogeneity via Semiparametric Mixture
cs.LG updates on arXiv.org
Target-Aware Interaction-Guided Reinforcement Learning for Black-Box Node Injection Attacks on Graph Neural Networks
Target-Aware Interaction-Guided Reinforcement Learning for Black-Box Node Injection Attacks on Graph Neural Networks
cs.LG updates on arXiv.org
Dictionaries, Not Darwin: Set-Level Selection Beats LLM Evolution in Scientific Equation Discovery
Dictionaries, Not Darwin: Set-Level Selection Beats LLM Evolution in Scientific Equation Discovery
cs.LG updates on arXiv.org
DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics
DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics
cs.LG updates on arXiv.org
Asymptotic-Preserving A Posteriori Analysis of Diffusion and Flow-Matching Samplers
Asymptotic-Preserving A Posteriori Analysis of Diffusion and Flow-Matching Samplers
cs.LG updates on arXiv.org
GlacierCastAI: Predicting Glacier Retreat from Multi-Modal Satellite Imagery and Climate Signals
GlacierCastAI: Predicting Glacier Retreat from Multi-Modal Satellite Imagery and Climate Signals
cs.LG updates on arXiv.org
Parametric Memory Decoding for Zero-Shot Routing in LoRA-Based External Parametric Memory
Parametric Memory Decoding for Zero-Shot Routing in LoRA-Based External Parametric Memory
cs.LG updates on arXiv.org
CertMix: Certified, Data-Efficient Metamaterial Design by Affine Mixing of Aligned Neural-Implicit Weight Spaces
CertMix: Certified, Data-Efficient Metamaterial Design by Affine Mixing of Aligned Neural-Implicit Weight Spaces
cs.LG updates on arXiv.org
MDL Meets Latent Confounders: LNML-based Causal Discovery
MDL Meets Latent Confounders: LNML-based Causal Discovery
cs.LG updates on arXiv.org
Masked Generative-Contrastive Representation Learning for Cross-Dataset EEG-Based Emotion Recognition
Masked Generative-Contrastive Representation Learning for Cross-Dataset EEG-Based Emotion Recognition
cs.LG updates on arXiv.org
Binary Iterative Method for Non-targeted Adversarial Attack
Binary Iterative Method for Non-targeted Adversarial Attack
cs.LG updates on arXiv.org
Mask-based Predictive Representations for Reinforcement Learning
Mask-based Predictive Representations for Reinforcement Learning
cs.LG updates on arXiv.org
Geometry of Ordinal Representations in Language Models
Geometry of Ordinal Representations in Language Models
cs.LG updates on arXiv.org
FedFFT: Taming Client Drift in Federated SAM via Spectral Perturbation Filtering
FedFFT: Taming Client Drift in Federated SAM via Spectral Perturbation Filtering
cs.LG updates on arXiv.org
Physics-Informed Graph Learning with Uncertainty Awareness for Open-Set Domain Generalization in Fault Diagnosis
Physics-Informed Graph Learning with Uncertainty Awareness for Open-Set Domain Generalization in Fault Diagnosis
cs.LG updates on arXiv.org
SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity
SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity
cs.LG updates on arXiv.org
Exploring Convolutional Neural Processes for Weather Downscaling
Exploring Convolutional Neural Processes for Weather Downscaling
cs.LG updates on arXiv.org
Channel-Adaptive Robust Aggregation for Over-the-Air Federated Learning in Heterogeneous Networks
Channel-Adaptive Robust Aggregation for Over-the-Air Federated Learning in Heterogeneous Networks
cs.LG updates on arXiv.org
Quantize the Target, Quantize the Drafter: Efficient Inference with Qwen3.5-4B
Quantize the Target, Quantize the Drafter: Efficient Inference with Qwen3.5-4B
cs.LG updates on arXiv.org
Signal or Noise? Understanding Generative Models for Real-World Sensor Time Series
Signal or Noise? Understanding Generative Models for Real-World Sensor Time Series
cs.LG updates on arXiv.org
On Preserving Geometrical Invariance for Superpixel Image Classification using Graph Transformer
On Preserving Geometrical Invariance for Superpixel Image Classification using Graph Transformer
cs.LG updates on arXiv.org
HiFA4: Training-Free 4-bit FlashAttention on Ascend HIF4 NPUs for LLM Inference
HiFA4: Training-Free 4-bit FlashAttention on Ascend HIF4 NPUs for LLM Inference
cs.LG updates on arXiv.org
SAD-LoRA: Spectral Alignment for Low-Rank Knowledge Distillation
SAD-LoRA: Spectral Alignment for Low-Rank Knowledge Distillation
cs.LG updates on arXiv.org
On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models
On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models
cs.LG updates on arXiv.org
Structure-Specific Representational Priors Causally Control the Grokking Delay
Structure-Specific Representational Priors Causally Control the Grokking Delay
cs.LG updates on arXiv.org
One Framework for All: Cross-Modal Membership Inference for Generative Models
One Framework for All: Cross-Modal Membership Inference for Generative Models
cs.LG updates on arXiv.org
How Many Initial Points Does Bayesian Optimization Need?
How Many Initial Points Does Bayesian Optimization Need?
cs.LG updates on arXiv.org
RL Forgets! Towards Continual Policy Optimization
RL Forgets! Towards Continual Policy Optimization
cs.LG updates on arXiv.org
NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation
NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation
cs.LG updates on arXiv.org
Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling
Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling
cs.LG updates on arXiv.org
Environmental Drivers of Respiratory Disease: A District Level Analysis
Environmental Drivers of Respiratory Disease: A District Level Analysis
cs.LG updates on arXiv.org
Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention
Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention
cs.LG updates on arXiv.org
Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation
Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation
cs.LG updates on arXiv.org
Knowledge-Informed Local Causal Discovery of Optimal Adjustment Sets
Knowledge-Informed Local Causal Discovery of Optimal Adjustment Sets
cs.LG updates on arXiv.org
A Deep Learning-based surrogate model for Severe Accidents in nuclear reactors using ASTEC
A Deep Learning-based surrogate model for Severe Accidents in nuclear reactors using ASTEC
cs.LG updates on arXiv.org
Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models
Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models
cs.LG updates on arXiv.org
Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning
Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning
cs.LG updates on arXiv.org
LeukocyteCount: Automatic Identification and Counting for leukocytes using Deep Learning
LeukocyteCount: Automatic Identification and Counting for leukocytes using Deep Learning
cs.LG updates on arXiv.org
Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders
Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders
cs.LG updates on arXiv.org
Beyond travel mode: urban context shapes active mobility's mental health effects over time
Beyond travel mode: urban context shapes active mobility's mental health effects over time
cs.LG updates on arXiv.org
Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic
Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic
cs.LG updates on arXiv.org
ManifoldFlow: SPD-Relaxed Stiefel Layers with Learnable Singular Spectrum
ManifoldFlow: SPD-Relaxed Stiefel Layers with Learnable Singular Spectrum
cs.LG updates on arXiv.org
Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Level Perturbation Representations
Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Level Perturbation Representations
cs.LG updates on arXiv.org
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
cs.LG updates on arXiv.org
Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning
Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning
cs.LG updates on arXiv.org
Score Distributions, Not Cells: Evaluating Single-Cell Perturbations Under Class Overlap
Score Distributions, Not Cells: Evaluating Single-Cell Perturbations Under Class Overlap
cs.LG updates on arXiv.org
Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One
Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One
cs.LG updates on arXiv.org
Measuring What Matters: A Unified Evaluation Framework for GNN Explainability
Measuring What Matters: A Unified Evaluation Framework for GNN Explainability
cs.LG updates on arXiv.org
Reliability and Identifiability in Persona-Trained Monte Carlo: Variance Decomposition, Stability Bounds, and the Identifiability of Heterogeneous News Reaction
Reliability and Identifiability in Persona-Trained Monte Carlo: Variance Decomposition, Stability Bounds, and the Identifiability of Heterogeneous News Reaction
cs.LG updates on arXiv.org
Machine Learning for Depression Screening and Intervention: an Original Circadian Rhythm Score-based Methodology
Machine Learning for Depression Screening and Intervention: an Original Circadian Rhythm Score-based Methodology
cs.LG updates on arXiv.org
A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
cs.LG updates on arXiv.org
URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment
URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment
cs.LG updates on arXiv.org
F-ACVAE: A Federated Adaptive Conditional Variational Auto-Encoder for Privacy-Preserving Intrusion Detection in IoT Networks
F-ACVAE: A Federated Adaptive Conditional Variational Auto-Encoder for Privacy-Preserving Intrusion Detection in IoT Networks
cs.LG updates on arXiv.org
Hierarchical Scaffolding Enables Human-Like Cognitive Selectivity under Data Scarcity
Hierarchical Scaffolding Enables Human-Like Cognitive Selectivity under Data Scarcity
cs.LG updates on arXiv.org
RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents
RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents
cs.LG updates on arXiv.org
Multi-Turn On-Policy Distillation with Prefix Replay
Multi-Turn On-Policy Distillation with Prefix Replay
cs.LG updates on arXiv.org
MARLIN: De Novo Molecular Structure Elucidation from Tandem Mass Spectra without a Ground-Truth Formula
MARLIN: De Novo Molecular Structure Elucidation from Tandem Mass Spectra without a Ground-Truth Formula
cs.LG updates on arXiv.org
Towards Personalized Differentially Private Learning for Decentralized Local Graphs
Towards Personalized Differentially Private Learning for Decentralized Local Graphs
cs.LG updates on arXiv.org
Predicting Drafted Deck Strength for "Magic: the Gathering"
Predicting Drafted Deck Strength for "Magic: the Gathering"
cs.LG updates on arXiv.org
Compressed Computation under $L^4$ Loss is likely Computation in Superposition
Compressed Computation under $L^4$ Loss is likely Computation in Superposition
cs.LG updates on arXiv.org
Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers
Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers
cs.LG updates on arXiv.org
KinEMbed: Decoding Kinematics from Electromyography via Cross-Modal Contrastive Learning
KinEMbed: Decoding Kinematics from Electromyography via Cross-Modal Contrastive Learning
cs.LG updates on arXiv.org
Probably Correct Optimal Stable Matching under Two-Sided Uncertainty
Probably Correct Optimal Stable Matching under Two-Sided Uncertainty
cs.LG updates on arXiv.org
Representing and Detecting Label Ambiguity in IMU-Based Exercise Evaluation
Representing and Detecting Label Ambiguity in IMU-Based Exercise Evaluation
cs.LG updates on arXiv.org
Pretraining Curricula Enable Selective Fine-tuning
Pretraining Curricula Enable Selective Fine-tuning
cs.LG updates on arXiv.org
Framework for Grouping Local Process Models
Framework for Grouping Local Process Models
cs.LG updates on arXiv.org
Enhancing the Forecasting Capability of Multi-Model Blending Algorithms for Extreme Precipitation via Joint Use of Station and Gridded Observations
Enhancing the Forecasting Capability of Multi-Model Blending Algorithms for Extreme Precipitation via Joint Use of Station and Gridded Observations
cs.LG updates on arXiv.org
Active Learning on Adversarially Corrupted Graphs
Active Learning on Adversarially Corrupted Graphs
cs.LG updates on arXiv.org
RL-Ballast: Ship Ballast Water Path Planning and Clog Prediction via Reinforcement Learning
RL-Ballast: Ship Ballast Water Path Planning and Clog Prediction via Reinforcement Learning
cs.LG updates on arXiv.org
When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters
When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters
cs.LG updates on arXiv.org
Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study
Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study
cs.LG updates on arXiv.org
Lightweight ML-Based Automatic Sleep Staging Framework with Constrained CNN and Mamba for Small-Sample EEG Datasets
Lightweight ML-Based Automatic Sleep Staging Framework with Constrained CNN and Mamba for Small-Sample EEG Datasets
cs.LG updates on arXiv.org
Sensitivity Sampling with Predictions for k-Means Clustering
Sensitivity Sampling with Predictions for k-Means Clustering
cs.LG updates on arXiv.org
Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM Training
Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM Training
cs.LG updates on arXiv.org
Geometry-Aware Bayesian Quantification via Compositional Data Analysis
Geometry-Aware Bayesian Quantification via Compositional Data Analysis
cs.LG updates on arXiv.org
Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control
Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control
cs.LG updates on arXiv.org
Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution
Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution
cs.LG updates on arXiv.org
Non-Convex Sparse Reinforcement Learning via Non-Monotone Inclusions
Non-Convex Sparse Reinforcement Learning via Non-Monotone Inclusions
cs.LG updates on arXiv.org
The Map Behind the Flow: Finite-Step Gradient Descent as a Dynamical System
The Map Behind the Flow: Finite-Step Gradient Descent as a Dynamical System
cs.LG updates on arXiv.org
ImputeECG: Deep Learning Reconstruction of Complete 12-Lead Electrocardiograms from Incomplete Recordings for Cardiac Assessment
ImputeECG: Deep Learning Reconstruction of Complete 12-Lead Electrocardiograms from Incomplete Recordings for Cardiac Assessment
cs.LG updates on arXiv.org
Hyperparameter Transfer in Graph Neural Networks
Hyperparameter Transfer in Graph Neural Networks
cs.LG updates on arXiv.org
Beyond Modality Fusion: Deep Ensembles for Multimodal Classification
Beyond Modality Fusion: Deep Ensembles for Multimodal Classification
cs.LG updates on arXiv.org
Uncertainty-aware damage identification in short-span bridges via physics-informed variational autoencoder
Uncertainty-aware damage identification in short-span bridges via physics-informed variational autoencoder
cs.LG updates on arXiv.org
CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion
CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion
cs.LG updates on arXiv.org
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
cs.LG updates on arXiv.org
Computing Monetary Risk Measures in Linear Time
Computing Monetary Risk Measures in Linear Time
cs.LG updates on arXiv.org
FAST: A Holistic Framework for Optimizing Memory-I/O, Computation, and Sampling in Temporal GNN Training
FAST: A Holistic Framework for Optimizing Memory-I/O, Computation, and Sampling in Temporal GNN Training
cs.LG updates on arXiv.org
Functional Bilevel Optimization for Predictive Fairness
Functional Bilevel Optimization for Predictive Fairness
cs.LG updates on arXiv.org
Counterfactual Methods for Detecting Unfairness in Anti-Money Laundering Algorithms
Counterfactual Methods for Detecting Unfairness in Anti-Money Laundering Algorithms
cs.LG updates on arXiv.org
Choosing a parallel heterogeneous ensemble method for tabular classification
Choosing a parallel heterogeneous ensemble method for tabular classification
cs.LG updates on arXiv.org
Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters
Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters
cs.LG updates on arXiv.org
Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing
Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing
cs.LG updates on arXiv.org
PDEFlow: Autonomous Agentic PDE Pipelines for Neural Operator Learning and Solver-Free Inference
PDEFlow: Autonomous Agentic PDE Pipelines for Neural Operator Learning and Solver-Free Inference
cs.LG updates on arXiv.org
Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech
Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech
cs.LG updates on arXiv.org
MeGA-MP: Metric Graph Advection Message Passing -- A Physics-Informed Message Passing Operator for Advection-Dominated Metric Graphs
MeGA-MP: Metric Graph Advection Message Passing -- A Physics-Informed Message Passing Operator for Advection-Dominated Metric Graphs
cs.LG updates on arXiv.org
Platonic Projection Structures: Operator-Induced Observability in Representation Learning
Platonic Projection Structures: Operator-Induced Observability in Representation Learning
cs.LG updates on arXiv.org
Relational Multi-Agent Reinforcement Learning for Dynamic Pricing in High-Speed Railway Markets
Relational Multi-Agent Reinforcement Learning for Dynamic Pricing in High-Speed Railway Markets
cs.LG updates on arXiv.org
SMART: A Machine Learning and Monte Carlo Framework for Rapid Analysis of Stochastic Transistor Aging and Process Variation in Digital Circuits
SMART: A Machine Learning and Monte Carlo Framework for Rapid Analysis of Stochastic Transistor Aging and Process Variation in Digital Circuits
cs.LG updates on arXiv.org
Latent Programming Horizons in Coding Agents
Latent Programming Horizons in Coding Agents
cs.LG updates on arXiv.org
Noisy-Channel Minimum Bayes Risk Decoding
Noisy-Channel Minimum Bayes Risk Decoding
cs.LG updates on arXiv.org
FlatManifold: Robust Continual Learning under Severe Label Noise and Domain Shifts via Intrinsic Manifold Flattening
FlatManifold: Robust Continual Learning under Severe Label Noise and Domain Shifts via Intrinsic Manifold Flattening
cs.LG updates on arXiv.org
Video-based detection of cessation of breathing in pre-term infants using machine learning
Video-based detection of cessation of breathing in pre-term infants using machine learning
cs.LG updates on arXiv.org
CanniUplift: A Holistic Framework for Mitigating Seller and Incentive Cannibalization in E-commerce Uplift Modeling
CanniUplift: A Holistic Framework for Mitigating Seller and Incentive Cannibalization in E-commerce Uplift Modeling
cs.LG updates on arXiv.org
FUSE: FK-Steered Multi-Modal Flow Matching for Efficient Simulation-Based Posterior Estimation
FUSE: FK-Steered Multi-Modal Flow Matching for Efficient Simulation-Based Posterior Estimation
cs.LG updates on arXiv.org
GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generation
GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generation
cs.LG updates on arXiv.org
Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach
Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach
cs.LG updates on arXiv.org
Adaptive Inference Batching using Policy Gradients
Adaptive Inference Batching using Policy Gradients
cs.LG updates on arXiv.org
Advances in Neural Controlled Differential Equations
Advances in Neural Controlled Differential Equations
cs.LG updates on arXiv.org
Air Quality Downscaling with Station-Guided Pseudo-Supervision
Air Quality Downscaling with Station-Guided Pseudo-Supervision
cs.LG updates on arXiv.org
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning
cs.LG updates on arXiv.org
Biologically Informed Deep Neural Networks for Multi-Omic Integration, Pathway Activity Inference and Risk Stratification in Cancer
Biologically Informed Deep Neural Networks for Multi-Omic Integration, Pathway Activity Inference and Risk Stratification in Cancer
cs.LG updates on arXiv.org
How Far is Too Far? Defining the Distance Threshold for Verification Siamese Networks
How Far is Too Far? Defining the Distance Threshold for Verification Siamese Networks
cs.LG updates on arXiv.org
TREK: Distill to Explore, Reinforce to Refine
TREK: Distill to Explore, Reinforce to Refine
cs.LG updates on arXiv.org
CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents
CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents
cs.LG updates on arXiv.org
TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning
TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning
cs.LG updates on arXiv.org
What Does a Discrete Diffusion Model Learn?
What Does a Discrete Diffusion Model Learn?
cs.LG updates on arXiv.org
Weak-to-Strong Generalization via Direct On-Policy Distillation
Weak-to-Strong Generalization via Direct On-Policy Distillation
cs.LG updates on arXiv.org
SiamixFormer: a fully-transformer Siamese network with temporal Fusion for accurate building detection and change detection in bi-temporal remote sensing images
SiamixFormer: a fully-transformer Siamese network with temporal Fusion for accurate building detection and change detection in bi-temporal remote sensing images
cs.LG updates on arXiv.org
miMamba: EEG-based Emotion Recognition with Multi-scale Inverted Mamba Models
miMamba: EEG-based Emotion Recognition with Multi-scale Inverted Mamba Models
cs.LG updates on arXiv.org
Inverse Design of Metainterfaces for Static Friction Control: Beyond the Hertzian Limit
Inverse Design of Metainterfaces for Static Friction Control: Beyond the Hertzian Limit
cs.LG updates on arXiv.org
Open-Weather Robust 3D Detection via Dual-Critic Diffusion Alignment
Open-Weather Robust 3D Detection via Dual-Critic Diffusion Alignment
cs.LG updates on arXiv.org
Tile-Level Activation Overlap for Efficient LLM Inference
Tile-Level Activation Overlap for Efficient LLM Inference
cs.LG updates on arXiv.org
Physics-Informed Domain-Invariant Feature Learning with Autoencoder-Driven Gaussian Clustering for Robust Non-line-of-Sight Scenarios
Physics-Informed Domain-Invariant Feature Learning with Autoencoder-Driven Gaussian Clustering for Robust Non-line-of-Sight Scenarios
cs.LG updates on arXiv.org
Beyond Satisfaction: Learning Associations Between Content, Reviews, and Well-Being
Beyond Satisfaction: Learning Associations Between Content, Reviews, and Well-Being
cs.LG updates on arXiv.org
Transformer-based Multisensor Data Fusion of Ultrasonic Guided Wave and FBG-based Strain Measurements for Multitask Aerospace Structural Health Monitoring
Transformer-based Multisensor Data Fusion of Ultrasonic Guided Wave and FBG-based Strain Measurements for Multitask Aerospace Structural Health Monitoring
cs.LG updates on arXiv.org
Interpretable machine learning predicts Parkinson's disease severity using motion-corrected QSM MRI and multiband multiecho fMRI features
Interpretable machine learning predicts Parkinson's disease severity using motion-corrected QSM MRI and multiband multiecho fMRI features
cs.LG updates on arXiv.org
MLSYSIM: First-Principles Infrastructure Modeling for Machine Learning Systems
MLSYSIM: First-Principles Infrastructure Modeling for Machine Learning Systems
cs.LG updates on arXiv.org
Uncertainty-Aware Last-Layer Adaptation of RETFound for Referable Diabetic Retinopathy Screening Under Dataset Shift
Uncertainty-Aware Last-Layer Adaptation of RETFound for Referable Diabetic Retinopathy Screening Under Dataset Shift
cs.LG updates on arXiv.org
From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving
From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving
cs.LG updates on arXiv.org
CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation
CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation
cs.LG updates on arXiv.org
The Moving Target: A Longitudinal Audit of Trustworthiness Drift Across Twelve Checkpoints of Open-Source Chat LLMs
The Moving Target: A Longitudinal Audit of Trustworthiness Drift Across Twelve Checkpoints of Open-Source Chat LLMs
cs.LG updates on arXiv.org
H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation
H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation
cs.LG updates on arXiv.org
CIPHER: Causal Intervention Pathways for Healthcare Equity and Robustness
CIPHER: Causal Intervention Pathways for Healthcare Equity and Robustness
cs.LG updates on arXiv.org
Scaling Weisfeiler-Leman Expressiveness Analysis to Massive Graphs with GPUs
Scaling Weisfeiler-Leman Expressiveness Analysis to Massive Graphs with GPUs
cs.LG updates on arXiv.org
Towards transferable lightweight neuromorphic computing through a model-free temporal-switch framework
Towards transferable lightweight neuromorphic computing through a model-free temporal-switch framework
cs.LG updates on arXiv.org
Privacy-Preserving Industrial Ergonomics: mmWave-Based Automated REBA Scoring and Pose Estimation
Privacy-Preserving Industrial Ergonomics: mmWave-Based Automated REBA Scoring and Pose Estimation
cs.LG updates on arXiv.org
Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers
Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers
cs.LG updates on arXiv.org
Schedulable Job-Level Dependencies for Cause-Effect Chains via Graph Neural Networks
Schedulable Job-Level Dependencies for Cause-Effect Chains via Graph Neural Networks
cs.LG updates on arXiv.org
SE-UNet: Singular Equivariant Imaging for Real-World Constrained Generation
SE-UNet: Singular Equivariant Imaging for Real-World Constrained Generation
cs.LG updates on arXiv.org
Benign Overfitting Does Not Occur in Diffusion Models
Benign Overfitting Does Not Occur in Diffusion Models
cs.LG updates on arXiv.org
Contaminated Multi-task Learning with Heterogeneity: Fundamental Limits and Optimal Algorithms
Contaminated Multi-task Learning with Heterogeneity: Fundamental Limits and Optimal Algorithms
cs.LG updates on arXiv.org
ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability
ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability
cs.LG updates on arXiv.org
RES-DARE: Failure-Aware Expert Adaptation and Rollback-Safe Self-Repair for Intrusion Detection
RES-DARE: Failure-Aware Expert Adaptation and Rollback-Safe Self-Repair for Intrusion Detection
cs.LG updates on arXiv.org
Property-Constrained 3D Porous Media Reconstruction from 2D Images via Conditional Generative Adversarial Networks
Property-Constrained 3D Porous Media Reconstruction from 2D Images via Conditional Generative Adversarial Networks
cs.LG updates on arXiv.org
Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models
Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models
cs.LG updates on arXiv.org
Provable Pruning for Efficient 3D Gaussian Splatting via Coresets
Provable Pruning for Efficient 3D Gaussian Splatting via Coresets
cs.LG updates on arXiv.org
Optimality-Informed Neural Networks for Lunar Landing Trajectory Optimization
Optimality-Informed Neural Networks for Lunar Landing Trajectory Optimization
cs.LG updates on arXiv.org
CodeJeNN: A simple C++ neural network generator for physics applications
CodeJeNN: A simple C++ neural network generator for physics applications
cs.LG updates on arXiv.org
Pretreatment MRI reveals a latent, molecular-subtype-independent structural phenotype that organizes treatment trajectories and recurrence risk
Pretreatment MRI reveals a latent, molecular-subtype-independent structural phenotype that organizes treatment trajectories and recurrence risk
cs.LG updates on arXiv.org
EvoOtter: Evolutionary Reproduction Test Generator
EvoOtter: Evolutionary Reproduction Test Generator
cs.LG updates on arXiv.org
SPLIT: Training-Free AI-Generated and Partially Edited Video Detection via Spatial Patch-Level Incoherence and Temporal Roughness
SPLIT: Training-Free AI-Generated and Partially Edited Video Detection via Spatial Patch-Level Incoherence and Temporal Roughness
cs.LG updates on arXiv.org
Selectivity Estimation for Linear Queries via Online Learning
Selectivity Estimation for Linear Queries via Online Learning
cs.LG updates on arXiv.org
Open Problem: Is Interaction Necessary for Order-Optimal 1-bit Mean Estimation?
Open Problem: Is Interaction Necessary for Order-Optimal 1-bit Mean Estimation?
cs.LG updates on arXiv.org
PromptPET: Privacy-Utility Optimized Prompt Obfuscation
PromptPET: Privacy-Utility Optimized Prompt Obfuscation
cs.LG updates on arXiv.org
Incentivizing Vision Language Models to Search for Long Video Question Answering
Incentivizing Vision Language Models to Search for Long Video Question Answering
cs.LG updates on arXiv.org
CONFLUX: A Latent Diusion Model for 3D Chest-CT Synthesis with RL Post-Training
CONFLUX: A Latent Diusion Model for 3D Chest-CT Synthesis with RL Post-Training
cs.LG updates on arXiv.org
HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion
HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion
cs.LG updates on arXiv.org
PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation
PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation
cs.LG updates on arXiv.org
Graph Neural Networks for the Graphical Bootstrap
Graph Neural Networks for the Graphical Bootstrap
cs.LG updates on arXiv.org
Dimension Reduction for Curves: Simplified and Generalized
Dimension Reduction for Curves: Simplified and Generalized
cs.LG updates on arXiv.org
Vidu S1: A Real-Time Interactive Video Generation Model
Vidu S1: A Real-Time Interactive Video Generation Model
cs.LG updates on arXiv.org
Open-Set Source Tracing as Compositional Factors via Structured Prototypes
Open-Set Source Tracing as Compositional Factors via Structured Prototypes
cs.LG updates on arXiv.org
An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures
An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures
cs.LG updates on arXiv.org
Which Algorithm Specification Formats Help Language Models Implement Machine Learning Algorithms?
Which Algorithm Specification Formats Help Language Models Implement Machine Learning Algorithms?
cs.LG updates on arXiv.org
Denoised Conformal Alignment for Reliable Selection of Conditional Average Treatment Effect Predictions
Denoised Conformal Alignment for Reliable Selection of Conditional Average Treatment Effect Predictions
cs.LG updates on arXiv.org
KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment
KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment
cs.LG updates on arXiv.org
Entropy Regularization Improves Policy Robustness in Continuous-Time Reinforcement Learning
Entropy Regularization Improves Policy Robustness in Continuous-Time Reinforcement Learning
cs.LG updates on arXiv.org
CRRL: A Causality-Based Reinforcement Learning Framework for Autonomous System Recovery
CRRL: A Causality-Based Reinforcement Learning Framework for Autonomous System Recovery
cs.LG updates on arXiv.org
Quantum Kolmogorov--Arnold representation theorem for continuous unitary-valued maps
Quantum Kolmogorov--Arnold representation theorem for continuous unitary-valued maps
cs.LG updates on arXiv.org
Scalable Maximal Frequent Episode Mining with Desbordante
Scalable Maximal Frequent Episode Mining with Desbordante
cs.LG updates on arXiv.org
Self-Specializing Vision-Language Transmon Chip Calibration in a Physics-Grounded Environment
Self-Specializing Vision-Language Transmon Chip Calibration in a Physics-Grounded Environment
cs.LG updates on arXiv.org
Seeing Through WiFi: Lightweight Human Pose Estimation with Dynamic Kernel Attention
Seeing Through WiFi: Lightweight Human Pose Estimation with Dynamic Kernel Attention
cs.LG updates on arXiv.org
Deriving Benchmarking Datasets from Long-Form Recordings: Challenges and Opportunities
Deriving Benchmarking Datasets from Long-Form Recordings: Challenges and Opportunities
cs.LG updates on arXiv.org
Complexity of Normalized Persistence Problems for Topological Data Analysis and Local Hamiltonians
Complexity of Normalized Persistence Problems for Topological Data Analysis and Local Hamiltonians
cs.LG updates on arXiv.org
Taste-aware music retrieval from audio embeddings
Taste-aware music retrieval from audio embeddings
cs.LG updates on arXiv.org
Piecewise Dynamic Diffusion Regularization for Reconstruction of Cardiac Cine MRI
Piecewise Dynamic Diffusion Regularization for Reconstruction of Cardiac Cine MRI
cs.LG updates on arXiv.org
Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types
Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types
cs.LG updates on arXiv.org
SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference
SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference
cs.LG updates on arXiv.org
Efficient Decentralized Multi-task Dataset Valuation via Model Merging
Efficient Decentralized Multi-task Dataset Valuation via Model Merging
cs.LG updates on arXiv.org
Pathways of Visual Information Flow in Vision-Language Models
Pathways of Visual Information Flow in Vision-Language Models
cs.LG updates on arXiv.org
CaSPECT: Discovering Causally Homogeneous Subgroups via Directed Spectral Clustering
CaSPECT: Discovering Causally Homogeneous Subgroups via Directed Spectral Clustering
cs.LG updates on arXiv.org
A Hierarchy of Policy Learning Problems
A Hierarchy of Policy Learning Problems
cs.LG updates on arXiv.org
When Aggregate Alignment Misleads: Auditing Policy Repair Without Per-State Expert Actions
When Aggregate Alignment Misleads: Auditing Policy Repair Without Per-State Expert Actions
cs.LG updates on arXiv.org
Scalable Differentially Private Data Compression via Diffusion and Stochastic Codes
Scalable Differentially Private Data Compression via Diffusion and Stochastic Codes
cs.LG updates on arXiv.org
From Mobile Data to Business Insights: An End-to-End Analytics Framework for Large-Scale Urban Mobility Analysis and Decision Support
From Mobile Data to Business Insights: An End-to-End Analytics Framework for Large-Scale Urban Mobility Analysis and Decision Support
cs.LG updates on arXiv.org
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
cs.LG updates on arXiv.org
ADP: Adversarial Dynamics Priors for Physically Grounded Humanoid Locomotion
ADP: Adversarial Dynamics Priors for Physically Grounded Humanoid Locomotion
cs.LG updates on arXiv.org
WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling
WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling
cs.LG updates on arXiv.org
CaresAI at SMM4H-HeaRD 2026: Predicting TNM Staging
CaresAI at SMM4H-HeaRD 2026: Predicting TNM Staging
cs.LG updates on arXiv.org
Reading Between the Dots: Decoding Hidden Computation across Filler Tokens
Reading Between the Dots: Decoding Hidden Computation across Filler Tokens