Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding Paper • 2608.07663 • Published 27 days ago • 23
K-EXAONE-2.0 Collection Journey to global frontier-scale foundation models • 5 items • Updated 28 days ago • 64
Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views Paper • 2606.29513 • Published Jun 28 • 53
Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking Paper • 2606.15673 • Published Apr 8 • 13
Rethinking State Tracking in Recurrent Models Through Error Control Dynamics Paper • 2605.07755 • Published May 8 • 24
UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations Paper • 2505.08787 • Published May 13, 2025 • 14
CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy Paper • 2504.07959 • Published Apr 10, 2025 • 10
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks Paper • 2501.08326 • Published Jan 14, 2025 • 34