中文nlp解决方案(大模型、数据、模型、训练、推理)

[CVPR2024] MMA-Diffusion: MultiModal Attack on Diffusion Models

TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, etc. It compresses deep learning models for downstream d…

[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs

[ICCV 2021] SynFace: Face Recognition with Synthetic Data

Official implementation for the arXiv paper "Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields"

GLM-4-Voice | 端到端中英语音对话模型

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

Evaling and unaligning Chinese LLM censorship

This repo is a live list of papers on game playing and large multimodality model - "A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges".

OpenTAD is an open-source temporal action detection (TAD) toolbox based on PyTorch.

A game theoretic approach to explain the output of any machine learning model.

CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) and 3) Simpl…

Bring portraits to life!

Open efforts to implement ChatGPT-like models and beyond.

This is the official implementation of "Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams"

Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.

[CVPR 2024 🔥] Official implementation of the paper "⏳ Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation"

MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation

[CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support LLaMA, Llama-2, BLOOM, Vicuna, Baichuan, etc.

Next generation face swapper and enhancer

ChatTTS is a generative speech model for daily dialogue.

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"

The second generation of YOWO action detector.

OCR, layout analysis, reading order, line detection in 90+ languages

MiniCPM-2B: An end-side LLM outperforms Llama2-13B.

Papers and resources related to the security and privacy of LLMs 🤖