The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 22 days ago • 161
WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control Paper • 2610.33135 • Published 25 days ago • 43
KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization Paper • 2610.14448 • Published Oct 10 • 36
Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI Paper • 2610.09146 • Published Oct 6 • 5
Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads Paper • 2610.05034 • Published Oct 4 • 9
Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL Paper • 2609.37200 • Published Sep 29 • 14
Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training Paper • 2609.07108 • Published 14 days ago • 18
WorldReward: Reward Modeling for Camera-Conditioned World Models Paper • 2609.03952 • Published Sep 3 • 16