Material for gpu-mode lectures

Official repository of ’Visual-RFT: Visual Reinforcement Fine-Tuning’

Official implementation of Inductive Moment Matching

[NeurIPS'24 Spotlight] Observational Scaling Laws

Unified Video Action Model

Enjoy the magic of Diffusion models!

Wan: Open and Advanced Large-Scale Video Generative Models

[ICLR 2025] Reconstructive Visual Instruction Tuning

MoBA: Mixture of Block Attention for Long-Context LLMs

Official PyTorch implementation for "Large Language Diffusion Models"

Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"

Code for "Diffusion Model Alignment Using Direct Preference Optimization"

Official Jax Implementation of MD4 Masked Diffusion Models

[CVPR23] A cascaded diffusion captioning model with a novel semantic-conditional diffusion process that upgrades conventional diffusion model with additional semantic prior.

A curated list for awesome discrete diffusion models resources.

[ICLR2025] DiffuGPT and DiffuLLaMA: Scaling Diffusion Language Models via Adaptation from Autoregressive Models

Simple and Effective Masked Diffusion Language Model

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

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Data and code for NeurIPS 2021 Paper "IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning".

Code for paper "Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning"

Geometry Question Solver (GeoS)

Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"

Fast Diffusion Models with Transformers

Code for "Differentiable Robot Rendering" (CoRL 2024)

HunyuanVideo: A Systematic Framework For Large Video Generation Model

[NeurIPS'24] This repository is the implementation of "SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models"

A high-throughput and memory-efficient inference and serving engine for LLMs

Janus-Series: Unified Multimodal Understanding and Generation Models