Skip to content

@thunlp THUNLP

Change the repository type filter

All

    Repositories list

    248 repositories

    • LLaVA-UHD

      Public
      LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer
      Python
      •
      Apache License 2.0
      •17•370•10•0•Updated Apr 1, 2025Apr 1, 2025

    • Migician

      Public
      Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models
      Python
      •
      MIT License
      •3•49•0•0•Updated Mar 31, 2025Mar 31, 2025

    • SICOG

      Public
      Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition
      1•24•0•0•Updated Mar 31, 2025Mar 31, 2025

    • ChartCoder

      Public
      ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation
      Python
      •1•29•0•0•Updated Mar 31, 2025Mar 31, 2025

    • DeepNote

      Public
      0•0•0•0•Updated Mar 27, 2025Mar 27, 2025

    • DeepPerception

      Public
      DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding
      Python
      •
      MIT License
      •0•39•0•0•Updated Mar 27, 2025Mar 27, 2025

    • ProactiveAgent

      Public
      A LLM-based Agent that predict its tasks proactively.
      Python
      •
      Apache License 2.0
      •29•342•2•0•Updated Mar 21, 2025Mar 21, 2025

    • Ouroboros

      Public
      Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
      Python
      •
      Apache License 2.0
      •10•95•3•0•Updated Mar 20, 2025Mar 20, 2025

    • FR-Spec

      Public
      FR-Spec: Frequency-Ranked Speculative Sampling
      C++
      •1•13•2•0•Updated Mar 20, 2025Mar 20, 2025

    • cost-optimal-gqa

      Public
      The code repository for the paper "Cost-Optimal Grouped-Query Attention for Long-Context LLMs"
      natural-language-processingtransformerllms
      1•1•1•0•Updated Mar 13, 2025Mar 13, 2025

    • TritonBench

      Public
      TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
      Python
      •
      Apache License 2.0
      •0•33•2•0•Updated Mar 3, 2025Mar 3, 2025

    • SchemaReinforcementLearning

      Public
      Learning to Generate STRUCTURED Output with Schema Reinforcement Learning
      Python
      •
      Apache License 2.0
      •1•6•0•0•Updated Mar 2, 2025Mar 2, 2025

    • APB

      Public
      C++
      •2•26•0•0•Updated Feb 22, 2025Feb 22, 2025

    • LLMxMapReduce

      Public
      Python
      •10•186•4•0•Updated Feb 21, 2025Feb 21, 2025

    • EmbodiedEval

      Public
      Evaluate Multimodal LLMs as Embodied Agents
      Python
      •
      MIT License
      •2•39•1•0•Updated Feb 14, 2025Feb 14, 2025

    • TAADpapers

      Public
      Must-read Papers on Textual Adversarial Attack and Defense
      adversarial-learningpaper-listadversarial-defensenlpnatural-language-processingadversarial-attacks
      Python
      •
      MIT License
      •195•1.5k•3•0•Updated Feb 3, 2025Feb 3, 2025

    • LEGENT

      Public
      Open Platform for Embodied Agents
      physics-enginerobot-simulatorlanguage-groundingembodied-ailarge-multimodal-models
      Python
      •
      Apache License 2.0
      •18•304•8•0•Updated Jan 12, 2025Jan 12, 2025

    • ACDiT

      Public
      ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
      Python
      •
      MIT License
      •1•30•2•0•Updated Dec 29, 2024Dec 29, 2024

    • Seq1F1B

      Public
      Sequence-level 1F1B schedule for LLMs.
      Python
      •
      Other
      •2.7k•16•0•0•Updated Dec 24, 2024Dec 24, 2024

    • KBAlign

      Public
      Codes for the paper: KBAlign - Efficient Self Adaptation on Specific Knowledge Bases
      Python
      •0•5•0•0•Updated Dec 9, 2024Dec 9, 2024

    • iAgents

      Public
      Python
      •2•32•0•0•Updated Dec 6, 2024Dec 6, 2024

    • Model_Emotion

      Public
      Neuron Activation
      Python
      •5•23•0•0•Updated Nov 21, 2024Nov 21, 2024

    • LEAD

      Public
      Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs (EMNLP 2024)
      Python
      •
      MIT License
      •0•6•0•0•Updated Nov 17, 2024Nov 17, 2024

    • Delta-CoMe

      Public
      Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024
      Python
      •
      Apache License 2.0
      •3•55•3•0•Updated Nov 16, 2024Nov 16, 2024

    • Optima

      Public
      Code for paper "Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System"
      Python
      •4•54•1•0•Updated Nov 14, 2024Nov 14, 2024

    • SparsingLaw

      Public
      The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".
      Python
      •
      MIT License
      •0•18•0•0•Updated Nov 12, 2024Nov 12, 2024

    • Chujian

      Public
      A large-scale dataset of Chu bamboo slip scripts and a multi-granularity tokenizer for ancient Chinese scripts
      Python
      •0•1•0•0•Updated Nov 12, 2024Nov 12, 2024

    • CA-LoRA

      Public
      CA-LoRA: Adapting Existing LoRA for Compressed LLMs to Enable Efficient Multi-Tasking on Personal Devices (COLM 2024)
      Python
      •0•6•0•0•Updated Oct 30, 2024Oct 30, 2024

    • ChatEval

      Public
      Codes for our paper "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"
      Python
      •
      Apache License 2.0
      •17•267•8•0•Updated Oct 19, 2024Oct 19, 2024

    • Adaptive-Note

      Public
      Python
      •6•53•5•0•Updated Oct 18, 2024Oct 18, 2024