Stars
LLM2CLIP makes SOTA pretrained CLIP model more SOTA ever.
Fast, differentiable sorting and ranking in PyTorch
A unified architecture deep learning framework designed specifically for ultra-large-scale sparse models.
Implementing DeepSeek R1's GRPO algorithm from scratch
A curated list for Efficient Large Language Models
list of efficient attention modules
[CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
[CVPR 2025 Highlight] The official CLIP training codebase of Inf-CL: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss". A super memory-efficiency CLIP training sc…
Fully open reproduction of DeepSeek-R1
K-Means clustering - constrained with minimum and maximum cluster size. Documentation: https://joshlk.github.io/k-means-constrained
Learning to Tokenize for Generative Retrieval (NeurIPS 2023)
Reformer, the efficient Transformer, in Pytorch
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.
MTEB: Massive Text Embedding Benchmark
HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
Code for ALBEF: a new vision-language pre-training method
Reading list for research topics in multimodal machine learning
A curated list of Multimodal Related Research.
✨✨Latest Advances on Multimodal Large Language Models
Official Implementation of Early-Learning Regularization Prevents Memorization of Noisy Labels
A toy large model for recommender system based on LLaMA2/SASRec/Meta's generative recommenders. Besides, note and experiments of official implementation for Meta's generative recommenders.