CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

✔（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Kolmogorov Arnold Networks

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Solve puzzles. Learn CUDA.

Reference PyTorch implementation and models for DINOv3

CoreNet: A library for training deep neural networks

A course on aligning smol models.

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

从无名小卒到大模型（LLM）大英雄~ 欢迎关注后续！！！

EPFL Machine Learning Course, Fall 2025

The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

TPAMI：Frequency-aware Feature Fusion for Dense Image Prediction

Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning

official implementation of "Interpreting CLIP's Image Representation via Text-Based Decomposition"

[NeurIPS 2025] Official code for JAFAR: Jack up Any Feature at Any Resolution

Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"

[NeurIPS '25 Spotlight] Official Pytorch implementation of "Vision Transformers Don't Need Trained Registers"

[TMLR] Public code repo for paper "A Single Transformer for Scalable Vision-Language Modeling"

code associated with ACL 2021 DExperts paper

[CVPR 2024] Offical implemention of the paper "DePT: Decoupled Prompt Tuning"

Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"