Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding Paper • 2604.26779 • Published 5 days ago • 8
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation Paper • 2604.11804 • Published 21 days ago • 71
mradermacher/gemma-4-E4B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-i1-GGUF 8B • Updated 13 days ago • 5.28k • 1
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 26 days ago • 323
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published about 1 month ago • 375
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published Mar 30 • 340
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models Paper • 2603.25716 • Published Mar 26 • 156
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models Paper • 2602.22859 • Published Feb 26 • 151