Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs Paper • 2605.09063 • Published May 9 • 82
SketchVLM: Vision language models can annotate images to explain thoughts and guide users Paper • 2604.22875 • Published Apr 23 • 38
Seeing Fast and Slow: Learning the Flow of Time in Videos Paper • 2604.21931 • Published Apr 23 • 19
Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items Paper • 2604.19748 • Published Apr 21 • 252
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation Paper • 2604.11804 • Published Apr 13 • 72