[NeurIPS 25] The official implementation of SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning

This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"

Code for ACL 2023 paper "Learning 'O' Helps for Learning More: Handling the Unlabeled Entity Problem for Class-incremental NER"

Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing

Crawl & visualize ICLR papers and reviews.

Code for EMNLP2020 long paper: BERT-Attack: Adversarial Attack Against BERT Using BERT

This toolkit was designed for the fast and efficient development of modern machine comprehension models, including both published models and original prototypes.

Reject complicated operations for incorporating lexicon for Chinese NER.

Lecture notes on Bayesian deep learning

Implementation of SimplE Embedding for Link Prediction in Knowledge Graphs in PyTorch

SimplE Embedding for Link Prediction in Knowledge Graphs

Source code for experiments in the papers "Complex Embeddings for Simple Link Prediction" (ICML 2016) and "Knowledge Graph Completion via Complex Tensor Factorization" (JMLR 2017).

An Open-Source Package for Neural Relation Extraction (NRE)

Neural Relation Extraction implemented in PyTorch

distant supervised relation extraction models: PCNN MIL (Zeng 2015), PCNN+ATT(Lin 2016). 关系抽取

A curated list of network embedding techniques.

LaTeX thesis template for Fudan University

pkuseg多领域中文分词工具; The pkuseg toolkit for multi-domain Chinese word segmentation

An annotated implementation of the Transformer paper.

A UI library by WeChat official design team, includes the most useful widgets/modules.

CSS3 animation library for wechat app.

Pytorch implementation of convolutional neural network visualization techniques

Visualization for Sequential Neural Networks with Attention

Code for the paper: Sentence-State LSTM for Text Representation

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Deformable Convolutional Networks

Pre-trained ELMo Representations for Many Languages