CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Paper
• 2602.01785 • Published
• 95
Coding
-
-
PingPong: A Natural Benchmark for Multi-Turn Code-Switching Dialogues
Paper • 2601.17277 • Published • 6 -
MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE
Paper • 2602.08961 • Published • 4 -
Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
Paper • 2603.02573 • Published • 11 -
Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges
Paper • 2506.02048 • Published