📹 A more flexible CogVideoX that can generate videos at any resolution and creates videos from images.

Official implementation of TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

No fortress, purely open ground. OpenManus is Coming.

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

3D Gaussian Splatting (3DGS) extension for Omniverse

Wan: Open and Advanced Large-Scale Video Generative Models

FlashMLA: Efficient MLA decoding kernels

[CVPR 2024] MemFlow: Optical Flow Estimation and Prediction with Memory

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Official implementation of ICCV2023 VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation

An ML research template with good documentation by Boyuan Chen, an MIT PhD student

Solve Visual Understanding with Reinforced VLMs

MoBA: Mixture of Block Attention for Long-Context LLMs

A debugging and profiling tool that can trace and visualize python code execution

https://huyenchip.com/ml-interviews-book/

[CVPR 2025] Official repository for “MagicArticulate: Make Your 3D Models Articulation-Ready”

Video Generation Foundation Models: https://saiyan-world.github.io/goku/

Stereo4D data processing pipeline

[CVPR 2024] Memory-based Adapters for Online 3D Scene Perception

News: the 10k dataset is ready for download.

Fillerbuster: Multi-View Scene Completion for Casual Captures

Seeing World Dynamics in a Nutshell

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

DELTA: Dense Efficient Long-range 3D Tracking for Any video (ICLR 2025)