CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents Paper • 2610.40799 • Published 24 days ago • 20
DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models Paper • 2610.35201 • Published 27 days ago • 15
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 27 days ago • 52
CRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful Enterprise Environments Paper • 2610.32004 • Published about 1 month ago • 9
Skeleton-Grounded Latent Action Model for Robot World Models Paper • 2610.31474 • Published Oct 22 • 3
Exploring the Limits of Combinatorial Generalization in Embodied Manipulation Paper • 2610.15425 • Published Oct 11 • 5
orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF Image-Text-to-Text • 177B • Updated 26 days ago • 673k • 1.56k
EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras Paper • 2610.03710 • Published Oct 2 • 8
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations Paper • 2609.20817 • Published Sep 17 • 9
Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking Paper • 2609.10745 • Published Sep 9 • 4
Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration Paper • 2609.01072 • Published Sep 2 • 5