CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering Paper • 2507.08776 • Published Jul 11 • 54
BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing Paper • 2506.17450 • Published Jun 20 • 63
Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning Paper • 2506.13654 • Published Jun 16 • 43
Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL Paper • 2505.02391 • Published May 5 • 25
