ChronoVision: Temporal Reasoning via Latent State Reconstruction Paper • 2608.05631 • Published 3 days ago • 32
NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap Paper • 2608.04397 • Published 4 days ago • 20
CAPEval: A Decoupled Caption Evaluation across Understanding and Generation Paper • 2608.02589 • Published 6 days ago • 25
Roomer: Reflective Object-Grounded Model Editing and Repair for 3D Indoor Layout Synthesis Paper • 2608.01973 • Published 6 days ago • 16