ChronoVision: Temporal Reasoning via Latent State Reconstruction Paper • 2608.05631 • Published 5 days ago • 38
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Paper • 2608.05747 • Published 5 days ago • 43
When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills Paper • 2608.03700 • Published 7 days ago • 9
PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning Paper • 2608.01837 • Published 8 days ago • 38
ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction Paper • 2607.29677 • Published 11 days ago • 23