Stars
LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement
[NeurIPS 2025] The Indra Representation Hypothesis for Multimodal Alignment
[ICLR 2026] Seeing Through Words: Controlling Visual Retrieval Quality with Language Models
Official code for Development of deep learning-based narrow-band imaging endocytoscopic classification for predicting colorectal lesions from a retrospective study (Nature Communications).
Source codes for the paper "Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark"
CLIP+MLP Aesthetic Score Predictor
Models and simulations for state space composition
The official implementation of paper "Can Textual Gradient Work in Federated Learning?" accepted at ICLR 2025
The official Pytorch implementation of paper "FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation" accepted by MICCAI 2023
Code and documentation to train Stanford's Alpaca models, and generate the data.
A Codebook-Driven Approach for Low-Light Image Enhancement
Open-source and strong foundation image recognition models.
Diffusion attentive attribution maps for interpreting Stable Diffusion.
Implementation of the Tolman Eichenbaum Machine in pytorch
[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.
Implementation of Graph Based Visual Saliency algorithm by J. Harel, C. Koch, and P. Perona
The official homepage of the COCO-Stuff dataset.
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations, CVPR 2019 (Oral)
这是一个deeplabv3-plus-pytorch的源码，可以用于训练自己的模型。
Papers from the intersection of deep learning and neuroscience
Putting Visual Object Recognition in Context