pytorch

EMNLP 2020: "Dialogue Response Ranking Training with Large-Scale Human Feedback Data"

Attribute (or cite) statements generated by LLMs back to in-context information.

A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).

Pretrain and finetune ELECTRA with fastai and huggingface. (Results of the paper replicated !)

A Compressed Stable Diffusion for Efficient Text-to-Image Generation [ECCV'24]

Vector AI — A platform for building vector based applications. Encode, query and analyse data using vectors.

🤗🖼️ HuggingPics: Fine-tune Vision Transformers for anything using images found on the web.

[CVPR 2023, Highlight] "NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° Views", Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Yi Wang, Zhangyang Wang

Open-source CLI, API, web UI, and reproducible benchmarks for probabilistic AI-generated image detection.

Multilingual TTS model with voice cloning and duration control, based on T5Gemma encoder-decoder LLM

PyTorch code for ETSformer: Exponential Smoothing Transformers for Time-series Forecasting

A friendly community offering free AI education.

Reliable, minimal and scalable library for pretraining foundation and world models

A Simple, Lightweight, and Extensible Serving Framework for X-AnyLabeling

PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" (https://arxiv.org/abs/2404.07143)

[CVPR 2023] LayoutDM: Discrete Diffusion Model for Controllable Layout Generation

Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023

FASHN VTON v1.5: Efficient Maskless Virtual Try-On in Pixel Space

PyTorch + HuggingFace code for RetoMaton: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including an implementation of kNN-LM and kNN-MT

Implementation of CVPR 2023 paper "Prompting Large Language Models with Answer Heuristics for Knowledge-based Visual Question Answering".