sysuyy

sysuyy's Stars

• riverstone496/awesome-second-order-optimization

  231

• OpenDriveLab/AgiBot-World

  World's First Large-scale High-quality Robotic Manipulation Benchmark

  Language:Python95168

• deepseek-ai/DeepSeek-V3

  Language:Python15k1.1k

• adalkiran/llama-nuts-and-bolts

  A holistic way of understanding how Llama and its components run in practice, with code and detailed documentation.

  Language:Go24111

• xichenpan/ARLDM

  Official Pytorch Implementation of Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models

  Language:Python19529

• BlinkDL/RWKV-LM

  RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

  Language:Python13k880

• OliverRensu/FlowAR

  “FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with any VAE.

  Language:Python632

• buoyancy99/diffusion-forcing

  code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

  Language:Python67332

• SimarKareer/EgoMimic

  Language:Jupyter Notebook422

• pytorch-labs/gpt-fast

  Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

  Language:Python5.7k520

• GAIR-NLP/O1-Journey

  O1 Replication Journey: A Strategic Progress Report – Part I

  1.8k54

• rom1504/img2dataset

  Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

  Language:Python3.8k347

• allenai/awesome-open-source-lms

  Friends of OLMo and their links.

  22714

• facebookresearch/flow_matching

  A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

  Language:Python1.7k64

• JunyaoHu/common_metrics_on_video_quality

  You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.

  Language:Python26510

• songweige/content-debiased-fvd

  [CVPR 2024] On the Content Bias in Fréchet Video Distance

  Language:Python1017

• chuanyangjin/fast-DiT

  Fast Diffusion Models with Transformers

  Language:Python770100

• ByteFlow-AI/TokenFlow

  🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".

  Language:Python2101

• omerbt/TokenFlow

  Official Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)

  Language:Python1.6k138

• minyoungg/platonic-rep

  Language:Python48532

• VideoVerses/VideoTuna

  Let's finetune video generation models!

  Language:Python34512

• Lightricks/LTX-Video

  Official repository for LTX-Video

  Language:Python2.4k180

• youngsheen/SimVQ

  SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer

  Language:Python1875

• mit-han-lab/vila-u

  VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

  Language:Python1913

• FoundationVision/VAR

  [NeurIPS 2024 Oral][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 yet state-of-the-art* codebase for autoregressive image generation!

  Language:Jupyter Notebook6.5k436

• bytedance/1d-tokenizer

  This repo contains the code for 1D tokenizer and generator

  Language:Jupyter Notebook62129

• ChaofanTao/Autoregressive-Models-in-Vision-Survey

  The paper collections for the autoregressive models in vision.

  34112

• PKU-YuanGroup/WF-VAE

  Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model

  Language:Python1046

• PKU-RL/CLIP4MC

  An RL-Friendly Vision-Language Model for Minecraft

  Language:Python292

• mihirp1998/VADER

  Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various reward models such as HPS, PickScore, VideoMAE, VJEPA, YOLO, Aesthetics etc.

  Language:Python22314