AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis Paper • 2610.13627 • Published 17 days ago • 14
OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs Paper • 2610.12461 • Published 18 days ago • 67
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published Sep 17 • 142
ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation Paper • 2609.09076 • Published Sep 8 • 25
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation Paper • 2609.08798 • Published Sep 8 • 82
HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF Image-Text-to-Text • 2B • Updated Aug 17 • 2.31M • 2.09k
orcarouter/Qwen3.8-27B-Uncensored-GGUF Image-Text-to-Text • 27B • Updated 14 days ago • 92.3k • 1.59k
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Paper • 2609.03796 • Published Sep 3 • 114
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science? Paper • 2608.19799 • Published Aug 20 • 69
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation Paper • 2608.17426 • Published Aug 18 • 160