This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"

Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's open notes for Codex, Claude Code, and Gemini.

A lightweight macOS literature manager built in native Swift.

Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis

SAM 3D Objects with Multi-view Images

[CVPR 2026] tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction

Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours

Pytorch implementation of Self-Refining Video Sampling

AI agents running research on single-GPU nanochat training automatically

Public code for XFactor: Introduces the first geometry-free model to achieve true self-supervised / pose-free Novel View Synthesis (NVS) by learning transferable latent camera pose representations.

[CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

Transform arXiv papers into a single LaTeX source that can be used as a prompt for asking LLMs questions about the paper.

Native and Compact Structured Latents for 3D Generation

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

An assortment of assets that demonstrate features and capabilities of the glTF format

[ICCV 2025] Official Implementation of Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics

abusing github commit history for the lulz

Config files for booting Mac OS 7-9, OS X and macOS on UTM emulator

Structured state space sequence models

GIF encoder based on libimagequant (pngquant). Squeezes maximum possible quality from the awful GIF format.

Point Animate by KIRI Engine

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

[ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

[ICML 2023] Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics

Dynamic Point Fields: Towards Efficient and Scalable Dynamic Surface Representations (ICCV 2023)