TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization Paper • 2601.16480 • Published 4 days ago • 49
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Paper • 2601.14724 • Published 6 days ago • 71
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs Paper • 2601.13836 • Published 7 days ago • 34
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm Paper • 2511.04570 • Published Nov 6, 2025 • 213