SALA: Semantically Aligned Latent Actions Enable Dual-Axis Scaling of Embodied Foundation Models Paper • 2611.17110 • Published 4 days ago • 16
More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs Paper • 2611.17610 • Published 6 days ago • 6
Energy-Based Reasoners: Your Recurrent Reasoner Should Be an Energy-Based Model Paper • 2611.08977 • Published 13 days ago • 10
PaperCritic: Training AI Reviewers to Assess the Soundness of Papers Paper • 2611.17834 • Published 6 days ago • 34
Invariant-Aware Harness Enforcement to Protect LLM Agents from Silent API Failures Paper • 2611.20595 • Published 3 days ago • 4
WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents Paper • 2611.17955 • Published 6 days ago • 13
GH-AWTrace: A Large-Scale Dataset of GitHub Agentic Workflow Execution Logs Paper • 2611.06866 • Published 15 days ago • 8
CANTraj: Recovering Vehicle Trajectories from CAN Signals in Naturalistic Driving Paper • 2611.18442 • Published 6 days ago • 5
Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models Paper • 2611.06982 • Published 15 days ago • 13
CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models Paper • 2607.24999 • Published 20 days ago • 6
ReproBridge: Building Reproducibility into ML Research Artifacts Paper • 2611.08452 • Published 14 days ago • 34
GTAGym: AAA Game Tasks Environment for Evaluation and Reinforcement Learning Paper • 2611.13028 • Published 8 days ago • 16
Incentivizing Self-Learning in Large Language Models via Reinforcement Learning Paper • 2610.39671 • Published 21 days ago • 35
Ensemble Routing for Prompt-Adaptive Cost-Aware LLM Inference Paper • 2611.10193 • Published 13 days ago • 15
WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative State Tracking in Large Language Models Paper • 2603.27343 • Published 20 days ago • 9
dNaViT: Discrete Codes are General-Purpose Visual Representations Paper • 2611.12426 • Published 10 days ago • 37
Few-Step Streaming Video Generation via Condition Shifting Paper • 2611.14033 • Published 9 days ago • 38
Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models Paper • 2611.06817 • Published 9 days ago • 37
VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding Paper • 2611.08449 • Published 14 days ago • 121