MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation Paper • 2605.27366 • Published 7 days ago • 24
Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration Paper • 2605.17423 • Published 16 days ago • 31
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published 11 days ago • 78
IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools Paper • 2605.20682 • Published 13 days ago • 83
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding Paper • 2605.27365 • Published 7 days ago • 129
UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards Paper • 2604.14967 • Published Apr 16 • 15
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning Paper • 2604.12374 • Published Apr 14 • 37
SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering Paper • 2604.11548 • Published Apr 13 • 22