VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images Paper • 2604.09531 • Published 9 days ago • 8
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding Paper • 2604.05015 • Published 13 days ago • 233
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 17 days ago • 864
FileGram: Grounding Agent Personalization in File-System Behavioral Traces Paper • 2604.04901 • Published 13 days ago • 40
A Simple Baseline for Streaming Video Understanding Paper • 2604.02317 • Published 17 days ago • 72
PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning Paper • 2603.26653 • Published 22 days ago • 18
HippoCamp: Benchmarking Contextual Agents on Personal Computers Paper • 2604.01221 • Published 17 days ago • 29
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models Paper • 2603.18118 • Published Mar 18 • 12