Pytorch implementation for Semantic Segmentation with multi models (Deeplabv3, Deeplabv3_plus, PSPNet, UNet, UNet_AutoEncoder, UNet_nested, R2AttUNet, AttentionUNet, RecurrentUNet,, SEGNet, CENet, …

Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents

One-shot Entropy Minimization

Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation

A MCP Server for Google Scholar: 🔍 Enable AI assistants to search and access Google Scholar papers through a simple MCP interface.

Benchmark for efficiency in memory and time of different KAN implementations.

A Python package that uses task-based neurons to build neural networks.

U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking

Code for PnP-Flow: Plug-and-Play image restoration with Flow Matching (ICLR 2025)

An official pytorch implementation of "Parallel Diffusion Model of Operator and Image for Blind Inverse Problems" (CVPR 2023)

A simple feature-based time series classifier using Kolmogorov–Arnold Networks

Our code for ICLR'25 paper "DataMan: Data Manager for Pre-training Large Language Models".

The evaluation framework for training-free sparse attention in LLMs

Experiments for distributed optimization algorithms

LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model (CVPR2024)

PyProximal – Proximal Operators and Algorithms in Python

Code for the paper LEGO-Prover: Neural Theorem Proving with Growing Libraries

OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM

Official code for "What Makes for Good Visual Tokenizers for Large Language Models?".

🔥Official PyTorch implementation for "LM4LV: A Frozen Large Language Model for Low-level Vision Tasks".

Topological transformer for protein-ligand complex interaction prediction.

Source code for the paper "Gradient Step Denoiser for convergent Plug-and-Play"

Unsupervised image segmentation by applying topological data analysis techniques.

FeatureAlignment = Alignment + Mechanistic Interpretability

Reproduction of the complete process of DeepSeek-R1 on small-scale models, including Pre-training, SFT, and RL.

A deep learning based method for solving high dimensional partial differential equations based on its weak form

Official code release of Hilbert Diffusion Model (PyTorch ver.)