FileGram: Grounding Agent Personalization in File-System Behavioral Traces Paper • 2604.04901 • Published 1 day ago • 17
A Simple Baseline for Streaming Video Understanding Paper • 2604.02317 • Published 5 days ago • 63
PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning Paper • 2603.26653 • Published 11 days ago • 16
HippoCamp: Benchmarking Contextual Agents on Personal Computers Paper • 2604.01221 • Published 6 days ago • 26
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models Paper • 2603.18118 • Published 20 days ago • 12
LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory Paper • 2603.03269 • Published Mar 3 • 62
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence Paper • 2603.07660 • Published 30 days ago • 85