Skip to content
Change the repository type filter

All

    Repositories list

    • LLaVA-UHD

      Public
      LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer
      Python
      Apache License 2.0
      17370100Updated 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
      34900Updated 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
      12400Updated Mar 31, 2025Mar 31, 2025
    • ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation
      Python
      12900Updated Mar 31, 2025Mar 31, 2025
    • DeepNote

      Public
      0000Updated Mar 27, 2025Mar 27, 2025
    • DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding
      Python
      MIT License
      03900Updated Mar 27, 2025Mar 27, 2025
    • A LLM-based Agent that predict its tasks proactively.
      Python
      Apache License 2.0
      2934220Updated Mar 21, 2025Mar 21, 2025
    • Ouroboros

      Public
      Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
      Python
      Apache License 2.0
      109530Updated Mar 20, 2025Mar 20, 2025
    • FR-Spec

      Public
      FR-Spec: Frequency-Ranked Speculative Sampling
      C++
      11320Updated Mar 20, 2025Mar 20, 2025
    • The code repository for the paper "Cost-Optimal Grouped-Query Attention for Long-Context LLMs"
      1110Updated Mar 13, 2025Mar 13, 2025
    • TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
      Python
      Apache License 2.0
      03320Updated Mar 3, 2025Mar 3, 2025
    • Learning to Generate STRUCTURED Output with Schema Reinforcement Learning
      Python
      Apache License 2.0
      1600Updated Mar 2, 2025Mar 2, 2025
    • APB

      Public
      C++
      22600Updated Feb 22, 2025Feb 22, 2025
    • Python
      1018640Updated Feb 21, 2025Feb 21, 2025
    • Evaluate Multimodal LLMs as Embodied Agents
      Python
      MIT License
      23910Updated Feb 14, 2025Feb 14, 2025
    • Must-read Papers on Textual Adversarial Attack and Defense
      Python
      MIT License
      1951.5k30Updated Feb 3, 2025Feb 3, 2025
    • LEGENT

      Public
      Open Platform for Embodied Agents
      Python
      Apache License 2.0
      1830480Updated Jan 12, 2025Jan 12, 2025
    • ACDiT

      Public
      ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
      Python
      MIT License
      13020Updated Dec 29, 2024Dec 29, 2024
    • Seq1F1B

      Public
      Sequence-level 1F1B schedule for LLMs.
      Python
      Other
      2.7k1600Updated Dec 24, 2024Dec 24, 2024
    • KBAlign

      Public
      Codes for the paper: KBAlign - Efficient Self Adaptation on Specific Knowledge Bases
      Python
      0500Updated Dec 9, 2024Dec 9, 2024
    • iAgents

      Public
      Python
      23200Updated Dec 6, 2024Dec 6, 2024
    • Neuron Activation
      Python
      52300Updated Nov 21, 2024Nov 21, 2024
    • LEAD

      Public
      Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs (EMNLP 2024)
      Python
      MIT License
      0600Updated Nov 17, 2024Nov 17, 2024
    • Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024
      Python
      Apache License 2.0
      35530Updated Nov 16, 2024Nov 16, 2024
    • Optima

      Public
      Code for paper "Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System"
      Python
      45410Updated Nov 14, 2024Nov 14, 2024
    • The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".
      Python
      MIT License
      01800Updated 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
      0100Updated 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
      0600Updated 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
      1726780Updated Oct 19, 2024Oct 19, 2024
    • Python
      65350Updated Oct 18, 2024Oct 18, 2024