HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Paper • 2601.14724 • Published 5 days ago • 68
MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents Paper • 2601.12346 • Published 8 days ago • 46
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs Paper • 2601.13836 • Published 6 days ago • 34
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development Paper • 2601.11077 • Published 10 days ago • 63
RoboOmni: Proactive Robot Manipulation in Omni-modal Context Paper • 2510.23763 • Published Oct 27, 2025 • 55