The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding Paper • 2502.08946 • Published 25 days ago • 182
DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization Paper • 2502.04370 • Published Feb 5 • 7
CustomVideoX: 3D Reference Attention Driven Dynamic Adaptation for Zero-Shot Customized Video Diffusion Transformers Paper • 2502.06527 • Published 28 days ago • 10
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Paper • 2502.06703 • Published 28 days ago • 142
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators Paper • 2502.06394 • Published 28 days ago • 86
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning Paper • 2502.06781 • Published 28 days ago • 60
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion Paper • 2502.08590 • Published 26 days ago • 40
Latent Radiance Fields with 3D-aware 2D Representations Paper • 2502.09613 • Published 25 days ago • 6
DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References Paper • 2502.09614 • Published 25 days ago • 12
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models Paper • 2502.06608 • Published 28 days ago • 32