Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach Paper • 2502.03639 • Published 2 days ago • 5 • 3
MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation Paper • 2502.04299 • Published 1 day ago • 8 • 3
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2 Paper • 2502.03544 • Published 3 days ago • 22 • 2
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis Paper • 2502.04128 • Published 2 days ago • 10 • 2
BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation Paper • 2502.03860 • Published 2 days ago • 10 • 2
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning Paper • 2502.03275 • Published 3 days ago • 9 • 2
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model Paper • 2502.02737 • Published 4 days ago • 132 • 3
Running on Zero 230 230 Chat with DeepSeek-VL2-small 🌍 Generate detailed responses using text and images
ACECODER: Acing Coder RL via Automated Test-Case Synthesis Paper • 2502.01718 • Published 5 days ago • 22 • 2
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models Paper • 2502.01061 • Published 5 days ago • 160 • 17
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning Paper • 2502.01100 • Published 5 days ago • 14 • 2
The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles Paper • 2502.01081 • Published 5 days ago • 9 • 2
Improving Transformer World Models for Data-Efficient RL Paper • 2502.01591 • Published 5 days ago • 8 • 2
MatAnyone: Stable Video Matting with Consistent Memory Propagation Paper • 2501.14677 • Published 15 days ago • 28 • 2
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming Paper • 2501.18837 • Published 8 days ago • 8 • 5