Maneesh Agrawala

8

Papers

64

Total Citations

Papers (8)

Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models

NeurIPS 2025arXiv

Keyframe-Guided Creative Video Inpainting

Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization

Disentangled3D: Learning a 3D Generative Model With Disentangled Geometry and Appearance From Monocular Images

Tree-Structured Shading Decomposition

Adding Conditional Control to Text-to-Image Diffusion Models

AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning

Measuring Compositional Consistency for Video Question Answering