The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 24 days ago • 52
OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding Paper • 2610.18829 • Published Oct 13 • 53
VideoJev: System One Model for Video Understanding and Interaction Paper • 2610.18615 • Published Oct 13 • 85
SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting Paper • 2610.04109 • Published Oct 2 • 21
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published Oct 1 • 40
RLE-Bench: A Qualifying Exam for Coding Agents as Robot Learning Engineers Paper • 2609.34210 • Published Sep 29 • 9