Highlights
- Pro
Stars
QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
Accessible large language models via k-bit quantization for PyTorch.
[IEEE TMI 2025] 3D MedDiffusion: A 3D Medical Diffusion Model for Controllable and High-quality Medical Image Generation
[NeurIPS 2025🔥]Main source code of SRPO framework.
TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation
NVIDIA Isaac GR00T N1.5 - A Foundation Model for Generalist Robots.
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
[CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
[NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.
A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
BiomedCLIP data pipeline
A curated collection of research and techniques for protecting intellectual property of large language models, including watermarking, fingerprinting, and more.
Stable Diffusion implemented from scratch in PyTorch
This is a implementation of the 3D FLAME model in PyTorch
Summary of publicly available ressources such as code, datasets, and scientific papers for the FLAME 3D head model
Processed / Cleaned Data for Paper Copilot
[ACL 2025 Main] MEraser: An Effective Fingerprint Erasure Approach for Large Language Models
PhyX: Does Your Model Have the "Wits" for Physical Reasoning?
Plant disease detection on PlantVillage dataset using EfficientNetV2-B0
Outlier detection (z-score and IQR) and visualization on Geolife dataset for transport mode detection task
Implementation of non-linear independent components estimation (NICE) in pytorch
Medical Diffusion: This repository contains the code to our paper Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Synthesis