HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Paper • 2601.14724 • Published 30 days ago • 74
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published 29 days ago • 90
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs Paper • 2601.13836 • Published about 1 month ago • 35
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development Paper • 2601.11077 • Published Jan 16 • 65
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI Paper • 2512.16676 • Published Dec 18, 2025 • 219
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm Paper • 2511.04570 • Published Nov 6, 2025 • 239
MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems Paper • 2505.18943 • Published May 25, 2025 • 24