-
Microsoft Research
- Redmond, Washington, US
- https://zinanlin.me
- @lin_zinan
Block or Report
Block or report fjxmlzn
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
Implementation of rectified flow and some of its followup research / improvements in Pytorch
[ECCV24] MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
Can LLMs Learn by Teaching? A Preliminary Study
The codebase of our paper "Improving the Training of Rectified Flows"
The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in th…
Official implementation of Cold-Diffusion for different transformations in pytorch.
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …
Geometric Computer Vision Library for Spatial AI
DSPy: The framework for programming—not prompting—foundation models
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unita…
SudoLang LLM Support for VSCode
⚡ InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)
Open-Sora: Democratizing Efficient Video Production for All
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.
The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)
[ICML 2024] Differentially Private Synthetic Data via Foundation Model APIs 2: Text