Skip to content
@LUMIA-Group

LUMIA: Language Understanding and Machine Intelligence Algorithms

LUMIA is a research group lead by Zhouhan Lin in Shanghai Jiao Tong University.

Popular repositories Loading

  1. Leveraging-Self-Supervised-Learning-for-AVSR Leveraging-Self-Supervised-Learning-for-AVSR Public

    Official PyTorch implementation of paper Leveraging Unimodal Self Supervised Learning for Multimodal Audio-Visual Speech Recognition (ACL 2022)

    Python 68 13

  2. rasat rasat Public

    Forked from ServiceNow/picard

    The official implementation of the paper "RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL"(EMNLP 2022)

    Python 65 17

  3. MemoryDecoder MemoryDecoder Public

    The official implementation of the paper "Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models" (NeurIPS 2025 Poster).

    Python 64 6

  4. OrderedGNN OrderedGNN Public

    The official implementation of the paper "Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing" (ICLR 2023).

    Python 47 5

  5. FourierTransformer FourierTransformer Public

    The official Pytorch implementation of the paper "Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator" (ACL 2023 Findings)

    Python 40 1

  6. PonderingLM PonderingLM Public

    Forked from hiyouga/LlamaFactory

    Official implementation of the paper "Pretraining Language Models to Ponder in Continuous Space"

    Python 24

Repositories

Showing 10 of 26 repositories
  • PonderLM-2 Public

    Official implementation of the paper "PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space"

    LUMIA-Group/PonderLM-2’s past year of commit activity
    Python 6 1 0 0 Updated Oct 24, 2025
  • ContextLM Public
    LUMIA-Group/ContextLM’s past year of commit activity
    Python 7 1 1 0 Updated Oct 16, 2025
  • AWM Public

    Official implementation of the paper "AWM: Accurate Weight-Matrix Fingerprint for Large Language Models"

    LUMIA-Group/AWM’s past year of commit activity
    Python 7 1 0 0 Updated Oct 9, 2025
  • MemoryDecoder Public

    The official implementation of the paper "Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models" (NeurIPS 2025 Poster).

    LUMIA-Group/MemoryDecoder’s past year of commit activity
    Python 64 Apache-2.0 6 1 0 Updated Sep 29, 2025
  • Anchor-Embedding Public

    The official implementation of the paper "Training LLMs to be Better Text Embedders through Bidirectional Reconstruction" (EMNLP 2025 Main Conference).

    LUMIA-Group/Anchor-Embedding’s past year of commit activity
    Python 8 0 0 0 Updated Aug 28, 2025
  • TosT5 Public

    The official implementation of the paper "Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training" (CIKM 2024).

    LUMIA-Group/TosT5’s past year of commit activity
    Python 3 MIT 1 0 0 Updated Aug 27, 2025
  • PonderingLM Public Forked from hiyouga/LlamaFactory

    Official implementation of the paper "Pretraining Language Models to Ponder in Continuous Space"

    LUMIA-Group/PonderingLM’s past year of commit activity
    Python 24 Apache-2.0 8,422 0 0 Updated Jul 21, 2025
  • HuRef Public

    Official implementation for "HuRef: HUman-REadable Fingerprint for Large Language Models" (NeurIPS2024)

    LUMIA-Group/HuRef’s past year of commit activity
    Python 15 3 0 0 Updated Jun 17, 2025
  • Gumbel-Reranking Public

    Official implementation for "Gumbel Reranking: Differentiable End-to-End Reranker Optimization" (ACL 2025 Main)

    LUMIA-Group/Gumbel-Reranking’s past year of commit activity
    Python 2 0 0 0 Updated May 20, 2025
  • SH2 Public

    The official implementation of the paper "SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully" (EMNLP 2024 Findings).

    LUMIA-Group/SH2’s past year of commit activity
    Python 2 0 0 0 Updated Apr 21, 2025

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Python Vue

Most used topics

Loading…