Researcher @Tencent-Hunyuan
LongMem. Official implementation of our NeurIPS 2023 paper "Augmenting Language Models with Long-Term Memory".
827Open-Qwen2VL. [COLM 2025] Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources
315MLM_Filter. Official implementation of our paper "Finetuned Multimodal Language Models are High-Quality Image-Text Data Filters".
71LLaVA-Llama-3. Reproduction of LLaVA-v1.5 based on Llama-3-8b LLM backbone.
64VaLM. VaLM: Visually-augmented Language Modeling. ICLR 2023.
56LLaVA-Unified. Python
22tod_as_nlg. Official implementation of SIGIR 2022 Paper "Task-Oriented Dialogue System as Natural Language Generation".
14zs-nmt-dae. Official implementation of EMNLP 2021 Paper "Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables"
12LaViA. Python
10grid-cells-pytorch. The pytorch implementation of grid cells network by Deepmind.
7UniFilter. [EMNLP 2025] UniFilter: A Unified Multimodal Data Quality Classifier for High-Quality Image-Text Interleaved and Caption Data Curation
5fast-weights-pytorch. PyTorch Implementation of the paper [Using Fast Weights to Attend to the Recent Past]
5STEPS.
1gridtorch. PYTORCH Implementation of the supervised learning experiments in Vector-based navigation using grid-like representations in artificial agents, as published at https://www.nature.com/articles/s41586-018-0102-6
1