CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models

[CVPR 2024] VkD : Improving Knowledge Distillation using Orthogonal Projections

[NeurIPS 2024] VeLoRA : Memory Efficient Training using Rank-1 Sub-Token Projections

MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model

AI一键批量生成各类短视频,自动批量混剪短视频,自动把视频发布到抖音,快手,小红书,视频号上,赚钱从来没有这么容易过! 支持本地语音模型chatTTS,fasterwhisper,GPTSoVITS,支持云语音：Azure,阿里云,腾讯云。支持Stable diffusion,comfyUI直接AI生图。Generate short videos with one click using A…

adds Sequence Parallelism into LLaMA-Factory

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Largest Interior/Inscribed Rectangle implementation in Python.

FreeStyle : Free Lunch for Text-guided Style Transfer using Diffusion Models

The code of our work "Golden Noise for Diffusion Models: A Learning Framework".

Lightweight nudity detection

State-of-the-art 2D and 3D Face Analysis Project

Steering Llama 2 with Contrastive Activation Addition

CoTracker is a model for tracking any point (pixel) on a video.

TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.

[ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

This is the official implementation of SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation.

[NeurIPS 2024] This is the official repo of the paper "Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-syncing DeepFakes".

Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs

[NeurIPS 2024 Best Paper][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ult…

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion, NeurIPS 2023 (spotlight)

Official repository for "VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide"

[NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers

[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling

This is the official implementation for DragVideo

Using pre-trained Diffusion models as priors for inference tasks

ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation (TMLR 2024)

[ICLR 2025] Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation

Official code for the paper "LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes".