Skip to content

@Alibaba-NLP Tongyi Lab, Alibaba Group

Change the repository type filter

All

    Repositories list

    43 repositories

    • VRAG

      Public
      Multimodal Retrieval-augmented Generation Framework Built by Tongyi Lab, Alibaba Group.
      Python
      •38•461•2•0•Updated Feb 17, 2026Feb 17, 2026

    • qqr

      Public
      qqr is an RL training framework for open-ended agents.
      Python
      •
      Apache License 2.0
      •20•213•1•0•Updated Feb 13, 2026Feb 13, 2026

    • DeepResearch

      Public
      Tongyi Deep Research, the Leading Open-source Deep Research Agent
      agentartificial-intelligencealibabaweb-agentinformation-seekingllmtongyideep-researchdeepresearch
      Python
      •
      Apache License 2.0
      •1.4k•18k•72•5•Updated Feb 7, 2026Feb 7, 2026

    • hilichurl

      Public
      Apache License 2.0
      •0•0•0•0•Updated Jan 13, 2026Jan 13, 2026

    • ViDoRAG

      Public
      [EMNLP 2025] ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents
      Python
      •49•630•1•1•Updated Jan 11, 2026Jan 11, 2026

    • VLLM-KB

      Public
      [EMNLP 2025] Code for "Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference"
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Jan 5, 2026Jan 5, 2026

    • E2Rank

      Public
      E2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker
      Python
      •
      Apache License 2.0
      •1•52•3•0•Updated Nov 4, 2025Nov 4, 2025

    • WebDetective

      Public
      A new evaluation paradigm for deep search that identifies specific LLM failure sources, introduces challenging hint-free datasets with holistic evaluation, and …
      Python
      •0•4•0•0•Updated Oct 14, 2025Oct 14, 2025

    • ZeroSearch

      Public
      ZeroSearch: Incentivize the Search Capability of LLMs without Searching
      Python
      •
      Apache License 2.0
      •115•1.2k•0•0•Updated Aug 16, 2025Aug 16, 2025

    • CHRONOS

      Public
      Repo for NAACL 2025 Paper "Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization"
      agentragtimeline-summarizationllm
      Python
      •32•292•2•0•Updated Aug 4, 2025Aug 4, 2025

    • LaRA

      Public
      The code for LaRA Benchmark
      Python
      •
      MIT License
      •3•47•0•0•Updated May 28, 2025May 28, 2025

    • MaskSearch

      Public
      Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"
      Python
      •7•149•1•0•Updated May 27, 2025May 27, 2025

    • OmniSearch

      Public
      Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent
      Python
      •30•413•11•1•Updated Apr 22, 2025Apr 22, 2025

    • CoFE-RAG

      Public
      Python
      •4•41•5•0•Updated Apr 11, 2025Apr 11, 2025

    • CDQA

      Public
      CDQA: Chinese Dynamic Question Answering Benchmark
      Python
      •0•17•1•0•Updated Dec 13, 2024Dec 13, 2024

    • Vec-RA-ODQA

      Public
      Source code of paper Improving "Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts
      Python
      •1•4•0•0•Updated Aug 30, 2024Aug 30, 2024

    • Key-Point-Analysis

      Public
      Python
      •0•1•0•0•Updated Apr 3, 2024Apr 3, 2024

    • RankingGPT

      Public
      code for paper 《RankingGPT: Empowering Large Language Models in Text Ranking with Progressive Enhancement》
      Python
      •2•34•4•0•Updated Jan 9, 2024Jan 9, 2024

    • SeqGPT

      Public
      SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding
      Python
      •
      Apache License 2.0
      •11•227•3•0•Updated Dec 13, 2023Dec 13, 2023

    • IBKD

      Public
      This is the official repository for the IBKD knowledge distillation method, as described in the paper .
      Python
      •
      GNU General Public License v3.0
      •2•2•0•0•Updated Nov 28, 2023Nov 28, 2023

    • EcomGPT

      Public
      An Instruction-tuned Large Language Model for E-commerce
      Python
      •18•265•9•1•Updated Sep 26, 2023Sep 26, 2023

    • MANNER

      Public
      [ACL 2023] MANNER: A Variational Memory-Augmented Model for Cross Domain Few-Shot Named Entity Recognition
      Python
      •0•20•6•0•Updated Jul 21, 2023Jul 21, 2023

    • StructuralKD

      Public
      [ACL-IJCNLP 2021] Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor
      named-entity-recognitiondependency-parserknowledge-distillation
      Python
      •
      Other
      •1•9•3•1•Updated Jul 10, 2023Jul 10, 2023

    • KB-NER

      Public
      Winner system (DAMO-NLP) of SemEval 2022 MultiCoNER shared task over 10 out of 13 tracks.
      nlpnamed-entity-recognitionsemevalnermultimodalsemeval-2022naacl2022
      Python
      •
      Other
      •21•187•17•1•Updated Jan 10, 2023Jan 10, 2023

    • Multi-CPR

      Public
      [SIGIR 2022] Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval
      pytorchdatasetquestion-answeringpassage-retrievaltext-rankingdense-retrievalpassage-ranking
      Python
      •19•201•4•0•Updated Jan 4, 2023Jan 4, 2023

    • ACE

      Public
      [ACL-IJCNLP 2021] Automated Concatenation of Embeddings for Structured Prediction
      sentiment-analysisnamed-entity-recognitionsequence-labelingdependency-parsingautomlneural-architecture-searchacl2021
      Python
      •
      Other
      •47•311•12•1•Updated Dec 2, 2022Dec 2, 2022

    • HiAGM

      Public
      Hierarchy-Aware Global Model for Hierarchical Text Classification
      text-classificationhierarchical-classificationgraph-neural-networks
      Python
      •
      MIT License
      •42•227•12•0•Updated Nov 28, 2022Nov 28, 2022

    • MultilangStructureKD

      Public
      [ACL 2020] Structure-Level Knowledge Distillation For Multilingual Sequence Labeling
      multilingualnlppytorchmrpnerknowledge-distillationbertsequence-labelingdependency-parsingacl2019
      Python
      •
      Other
      •9•72•0•1•Updated Nov 23, 2022Nov 23, 2022

    • CLNER

      Public
      [ACL-IJCNLP 2021] Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning
      named-entity-recognition
      Python
      •
      Other
      •15•93•2•1•Updated Nov 20, 2022Nov 20, 2022

    • AIN

      Public
      Code for our EMNLP 2020 Paper "AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network"
      Python
      •
      Other
      •3•19•0•1•Updated Nov 14, 2022Nov 14, 2022