HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Paper • 2601.14724 • Published 3 days ago • 58
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published 2 days ago • 66
Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs Paper • 2512.07525 • Published Dec 8, 2025 • 59
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm Paper • 2511.04570 • Published Nov 6, 2025 • 212
JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence Paper • 2510.23538 • Published Oct 27, 2025 • 97
RoboOmni: Proactive Robot Manipulation in Omni-modal Context Paper • 2510.23763 • Published Oct 27, 2025 • 55
Sparser Block-Sparse Attention via Token Permutation Paper • 2510.21270 • Published Oct 24, 2025 • 25
Sparser Block-Sparse Attention via Token Permutation Paper • 2510.21270 • Published Oct 24, 2025 • 25 • 1
LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models Paper • 2510.13626 • Published Oct 15, 2025 • 46