Skip to content

@VITA-Group VITA

Change the repository type filter

All

    Repositories list

    203 repositories

    • READ-ME

      Public
      0•0•0•0•Updated Oct 16, 2024Oct 16, 2024

    • MM3DGS-SLAM

      Public
      [IROS 2024] MM3DGS SLAM: Multi-modal 3D Gaussian Splatting for SLAM Using Vision, Depth, and Inertial Measurements
      roboticsslamgaussian-splatting
      Python
      •
      Other
      •8•88•2•0•Updated Oct 16, 2024Oct 16, 2024

    • VITA-Group.github.io

      Public
      Jupyter Notebook
      •3•4•0•0•Updated Oct 14, 2024Oct 14, 2024

    • LightGaussian

      Public
      [NeurIPS 2024 Spotlight]"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
      3d-reconstructionefficient-inferencegaussian-splattingnuripsneurips-2024
      Python
      •
      Other
      •50•566•18•1•Updated Oct 12, 2024Oct 12, 2024

    • o1-planning

      Public
      On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability
      planningopenaireasoningfoundation-modelsllm
      Python
      •1•14•0•0•Updated Oct 2, 2024Oct 2, 2024

    • vitagpt-teachersday2024

      Public
      VitaGPT: A tailored AI assistant in honor of Teacher's Day 2024 created by all vita members
      Python
      •0•1•0•0•Updated Sep 10, 2024Sep 10, 2024

    • LoCoCo

      Public
      [ICML‘2024] "LoCoCo: Dropping In Convolutions for Long Context Compression", Ruisi Cai, Yuandong Tian, Zhangyang Wang, Beidi Chen
      Python
      •0•11•2•0•Updated Sep 7, 2024Sep 7, 2024

    • LLaGA

      Public
      [ICML2024] "LLaGA: Large Language and Graph Assistant", Runjin Chen, Tong Zhao, Ajay Jaiswal, Neil Shah, Zhangyang Wang
      Python
      •
      Apache License 2.0
      •3•70•2•0•Updated Sep 4, 2024Sep 4, 2024

    • Diffusion4D

      Public
      "Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models", Hanwen Liang*, Yuyang Yin*, Dejia Xu, Hanxue Liang, Zhangyang Wang, Konstantinos N. Plataniotis, Yao Zhao, Yunchao Wei
      4dgenerative-aitext-to-4dimage-to-4d
      Python
      •3•222•0•0•Updated Sep 1, 2024Sep 1, 2024

    • Comp4D

      Public
      "Comp4D: Compositional 4D Scene Generation", Dejia Xu*, Hanwen Liang*, Neel P. Bhatt, Hezhen Hu, Hanxue Liang, Konstantinos N. Plataniotis, and Zhangyang Wang
      4dgenerative-aigaussian-splattingtext-to-4d
      Python
      •1•71•3•0•Updated Aug 25, 2024Aug 25, 2024

    • RankMean

      Public
      Python
      •0•2•1•0•Updated Jul 25, 2024Jul 25, 2024

    • NeRF-SOS

      Public
      [ICLR2023] "NeRF-SOS: Any-View Self-supervised Object Segmentation from Complex Real-World Scenes", Zhiwen Fan, Peihao Wang, Xinyu Gong, Yifan Jiang, Dejia Xu, Zhangyang Wang
      segmentationnerfself-supervised-learning
      Python
      •
      MIT License
      •13•131•1•0•Updated Jul 22, 2024Jul 22, 2024

    • WeLore

      Public
      From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients. Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu, Jiawei Zhao, Yuandong Tian, Zhangyang Wang
      Python
      •1•43•0•0•Updated Jul 18, 2024Jul 18, 2024

    • Q-GaLore

      Public
      Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.
      quantizationlow-ranklarge-language-modelsmemory-efficient-learning
      Python
      •
      Apache License 2.0
      •13•164•6•1•Updated Jul 17, 2024Jul 17, 2024

    • 4DGen

      Public
      "4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency", Yuyang Yin*, Dejia Xu*, Zhangyang Wang, Yao Zhao, Yunchao Wei
      4dgenerative-aigaussian-splattingimage-to-4d
      Python
      •10•213•3•0•Updated Jun 24, 2024Jun 24, 2024

    • SparseCocktail

      Public
      0•1•0•0•Updated Jun 22, 2024Jun 22, 2024

    • Shake-to-Leak

      Public
      Python
      •
      MIT License
      •1•13•1•0•Updated Jun 22, 2024Jun 22, 2024

    • Q-Hitter

      Public
      Python
      •
      MIT License
      •0•8•2•0•Updated Jun 4, 2024Jun 4, 2024

    • Junk_DNA_Hypothesis

      Public
      [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, Souvik Kundu, Zhangyang Wang
      Python
      •2•15•0•0•Updated Jun 2, 2024Jun 2, 2024

    • DP-OPT

      Public
      [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
      privacyllamatransfer-learninggradiovicunaprompt-tuningllmprompt-engineeringchatgpt
      Python
      •
      MIT License
      •9•30•1•1•Updated May 30, 2024May 30, 2024

    • ProgressiveDD

      Public
      [ICLR 2024] "Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality" by Xuxi Chen*, Yu Yang*, Zhangyang Wang, Baharan Mirzasoleiman
      dataset-distillation
      Python
      •0•9•0•0•Updated May 18, 2024May 18, 2024

    • Ms-PoE

      Public
      "Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding" Zhenyu Zhang, Runjin Chen, Shiwei Liu, Zhewei Yao, Olatunji Ruwase, Beidi Chen, Xiaoxia Wu, Zhangyang Wang.
      positional-encodinglarge-language-modelslong-contextlost-in-the-middle
      Python
      •
      MIT License
      •2•20•3•1•Updated May 7, 2024May 7, 2024

    • EnlightenGAN

      Public
      [IEEE TIP] "EnlightenGAN: Deep Light Enhancement without Paired Supervision" by Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang
      pytorchganunsupervised-learninggenerative-adversarial-networkslow-lightlow-light-enhance
      Python
      •
      Other
      •201•925•17•0•Updated Apr 25, 2024Apr 25, 2024

    • ViHGNN

      Public
      [ICCV2023] "Vision HGNN: An Image is More than a Graph of Nodes" by Yan Han, Peihao Wang, Souvik Kundu, Ying Ding, and Zhangyang Wang
      Python
      •
      MIT License
      •7•38•10•0•Updated Apr 9, 2024Apr 9, 2024

    • GNT

      Public
      [ICLR 2023] "Is Attention All NeRF Needs?" by Mukund Varma T*, Peihao Wang* , Xuxi Chen, Tianlong Chen, Subhashini Venugopalan, Zhangyang Wang
      transformerneural-renderingneural-radiance-fields
      Python
      •
      MIT License
      •25•339•10•0•Updated Apr 3, 2024Apr 3, 2024

    • llm-kick

      Public
      [ICLR 2024] Jaiswal, A., Gan, Z., Du, X., Zhang, B., Wang, Z., & Yang, Y. Compressing llms: The truth is rarely pure and never simple.
      llm-inferencellm-evaluationllm-compressionllm-pruning
      Python
      •3•16•0•0•Updated Mar 13, 2024Mar 13, 2024

    • FSGS

      Public
      [ECCV 2024]"FSGS: Real-Time Few-Shot View Synthesis using Gaussian Splatting", Zehao Zhu*, Zhiwen Fan*, Yifan Jiang, Zhangyang Wang
      Python
      •
      Other
      •32•386•24•0•Updated Feb 27, 2024Feb 27, 2024

    • LiGO

      Public
      [ICLR 2023] "Learning to Grow Pretrained Models for Efficient Transformer Training" by Peihao Wang, Rameswar Panda, Lucas Torroba Hennigen, Philip Greengard, Leonid Karlinsky, Rogerio Feris, David Cox, Zhangyang Wang, Yoon Kim
      transformersefficient-traininglarge-language-modelsmodel-reusing
      Python
      •
      MIT License
      •9•81•0•0•Updated Feb 26, 2024Feb 26, 2024

    • HardFocusTraining

      Public
      [Preprint] "Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization" by Xuxi Chen, Zhendong Wang, Daouda Sow, Junjie Yang, Tianlong Chen, Yingbin Liang, Mingyuan Zhou, Zhangyang Wang
      Python
      •1•4•1•0•Updated Feb 20, 2024Feb 20, 2024

    • principled_scaling_lr_init

      Public
      Python
      •
      MIT License
      •0•6•0•0•Updated Feb 12, 2024Feb 12, 2024