GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published 14 days ago • 47
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Paper • 2609.38721 • Published 14 days ago • 274
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States Paper • 2610.01415 • Published 13 days ago • 92