Appear2Meaning: A Cross-Cultural Benchmark for Structured Cultural Metadata Inference from Images Paper • 2604.07338 • Published 8 days ago • 5
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 8 days ago • 310
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published 13 days ago • 355
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published 17 days ago • 339
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models Paper • 2603.17051 • Published 29 days ago • 109
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Paper • 2603.16859 • Published 29 days ago • 248