Covering Human Action Space for Computer Use: Data Synthesis and Benchmark Paper • 2605.12501 • Published 7 days ago • 14
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation Paper • 2605.10912 • Published 8 days ago • 45
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding Paper • 2604.26779 • Published 20 days ago • 13
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation Paper • 2604.11804 • Published Apr 13 • 72
mradermacher/gemma-4-E4B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-i1-GGUF 8B • Updated 28 days ago • 1.92k • 1
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 324
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published Apr 3 • 628
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published Mar 30 • 342
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models Paper • 2603.25716 • Published Mar 26 • 156