In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks Paper • 2609.38173 • Published 13 days ago • 48
ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience Paper • 2610.05303 • Published 8 days ago • 23
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF Image-Text-to-Text • 117B • Updated 12 days ago • 679k • 375
OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport Paper • 2609.36602 • Published 13 days ago • 8
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents Paper • 2609.17708 • Published 27 days ago • 78
EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents Paper • 2609.05903 • Published Sep 5 • 65
Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks Paper • 2609.08404 • Published Sep 8 • 24
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Paper • 2609.03796 • Published Sep 3 • 182
AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss Paper • 2608.11205 • Published Aug 11 • 27
Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness Paper • 2608.09766 • Published Aug 10 • 5