Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

NVIDIA FastGen: Fast Generation from Diffusion Models

Sharp Monocular View Synthesis in Less Than a Second

Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"

https://coshand.cs.columbia.edu/

A refactored codebase for Gaussian Splatting. Training 3DGS in 50 seconds!

This is official repository for OLATverse

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning

Code for project Fiducial Exoskeletons: Image-Centric Robot State Estimation!

Code for SIRE: SE(3) Intrinsic Rigidity Embeddings

[ICLR 2026] Generative View Stitching

[ICLR 2025 Oral] Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Depth Anything 3

rCM: SOTA JVP-Based Diffusion Distillation & Few-Step Video Generation & Scaling Up sCM/MeanFlow

ComfyUI pi-Flow nodes for fast few-step sampling

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

[ICLR 2026] pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation

[ICLR 2026] Trace Anything: Representing Any Video in 4D via Trajectory Fields

Official code for paper "InstantSfM: Fully Sparse and Parallel Structure-from-Motion"

A simple state update rule to enhance length generalization for CUT3R

[NeurIPS 2025] PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

[ICLR 2026] Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video