Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

[ICML'25 Oral] Multi-agent Architecture Search via Agentic Supernet

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.

Code, Data and Model for Paper "Learning from Peers in Reasoning Models"

A collection of MCP servers.

Evaluating the faithfulness of long-context language models

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

Evaluating ChatGPT’s Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness

骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技

记录NLP、CV、搜索、推荐等AI岗位最新情况。

CCL 2022 汉语学习者文本纠错评测

Yet Another Chinese Learner Corpus

Collections of Chinese NLP corpus

Sentiment-annotated Persuasive Opinion Multimedia (POM) dataset

Code and dataset for the paper "Mining fine-grained opinions on closed captions of YouTube videos with an attention-RNN"

Multi-Interactive Memory Network for Aspect Based Multimodal Sentiment Analysis - AAAI 2019

Dataset for WWW 2020 paper "Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog"

A PyTorch-based knowledge distillation toolkit for natural language processing

☁️ Build multimodal AI applications with cloud-native stack

NLP超强入门指南，包括各任务sota模型汇总（文本分类、文本匹配、序列标注、文本生成、语言模型），以及代码、技巧

近年来事件抽取方法总结，包括中文事件抽取、开放域事件抽取、事件数据生成、跨语言事件抽取、小样本事件抽取、零样本事件抽取等类型，DMCNN、FramNet、DLRNN、DBRNN、GCN、DAG-GRU、JMEE、PLMEE等方法

中文地址分词（地址元素识别与抽取），通过序列标注进行NER

In this project we develop new deep learning models for bootstrapping language understanding models for languages with no labeled data using labeled data from other languages.