Skip to content

@VITA-Group VITA

Change the repository type filter

All

    Repositories list

    216 repositories

    • Oscillation-Inversion

      Public
      [AAAI'26 Oral] Oscillation Inversion: Training-free Image and Video Enhancement through Oscillated Latents in Large Flow Models
      MIT License
      •0•1•1•0•Updated Nov 16, 2025Nov 16, 2025

    • LoX

      Public
      [COLM 2025] LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
      ailow-rankllm-safety
      Python
      •
      MIT License
      •0•5•2•0•Updated Nov 13, 2025Nov 13, 2025

    • WeLore

      Public
      [ICML 2025] From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications
      Python
      •1•51•1•0•Updated Oct 30, 2025Oct 30, 2025

    • Neon

      Public
      Python
      •
      MIT License
      •2•14•0•0•Updated Oct 7, 2025Oct 7, 2025

    • VLM-3R

      Public
      VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
      Python
      •
      Other
      •22•295•6•0•Updated Sep 1, 2025Sep 1, 2025

    • WFM-TTS

      Public
      [COLM 2025] Can Test-Time Scaling Improve World Foundation Model?
      Jupyter Notebook
      •0•7•0•0•Updated Aug 13, 2025Aug 13, 2025

    • o1-planning

      Public
      [NeurIPS'24 LanGame workshop] On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability
      planningopenaireasoningfoundation-modelsllm
      Python
      •1•41•0•0•Updated Jul 7, 2025Jul 7, 2025

    • VITA-Group.github.io

      Public
      Jupyter Notebook
      •3•4•0•0•Updated Jul 2, 2025Jul 2, 2025

    • 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
      •12•61•4•0•Updated Jun 13, 2025Jun 13, 2025

    • TAPE

      Public
      [ICML'25] "Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding" by Jiajun Zhu, Peihao Wang, Ruisi Cai, Jason D. Lee, Pan Li, Zhangyang Wang
      positional-encodinglarge-language-modelsequivariant-neural-networks
      Python
      •
      MIT License
      •2•14•1•0•Updated Jun 6, 2025Jun 6, 2025

    • E3D-Bench

      Public
      Official implementation of "E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models"
      1•102•2•0•Updated Jun 4, 2025Jun 4, 2025

    • principled_scaling_lr_init

      Public
      [ICLR 2024] Principled Architecture-aware Scaling of Hyperparameters
      Python
      •
      MIT License
      •0•6•0•0•Updated Jun 1, 2025Jun 1, 2025

    • SteepGS

      Public
      [CVPR 2025] Steepest Descent Density Control for Compact 3D Gaussian Splatting
      JavaScript
      •0•4•0•0•Updated May 15, 2025May 15, 2025

    • R-Sparse

      Public
      [ICLR'25] R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
      sparsityllmllm-inference
      Python
      •2•14•2•0•Updated Apr 28, 2025Apr 28, 2025

    • 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•16•0•0•Updated Apr 21, 2025Apr 21, 2025

    • 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
      •6•25•0•0•Updated Apr 21, 2025Apr 21, 2025

    • SEAL

      Public
      [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free
      Python
      •4•45•3•0•Updated Apr 6, 2025Apr 6, 2025

    • SSM-Bottleneck

      Public
      [ICLR'25] "Understanding Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing" by Peihao Wang, Ruisi Cai, Yuehao Wang, Jiajun Zhu, Pragya Srivastava, Zhangyang Wang, Pan Li
      language-modelstate-space-modeloversmoothingrecency-bias
      Python
      •
      MIT License
      •1•17•0•0•Updated Mar 21, 2025Mar 21, 2025

    • Shake-to-Leak

      Public
      [SatML 2024] Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
      Python
      •
      MIT License
      •3•15•2•0•Updated Mar 15, 2025Mar 15, 2025

    • Superficial_Alignment

      Public
      [NAACL 2025] Extracting and Understanding the Superficial Knowledge in Alignment, Runjin Chen, Gabriel Jacob Perin, Xuxi Chen, Xilun Chen, Yan Han, Nina S. T. Hirata , Junyuan Hong, Bhavya Kailkhura
      Python
      •0•5•0•0•Updated Jan 25, 2025Jan 25, 2025

    • VideoLifter

      Public
      [3DV 2026] VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment
      Python
      •
      Apache License 2.0
      •3•137•3•1•Updated Jan 21, 2025Jan 21, 2025

    • Diffusion4D

      Public
      [NeurIPS 2024] Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models
      4dgenerative-aitext-to-4dimage-to-4d
      Python
      •7•327•6•0•Updated Jan 21, 2025Jan 21, 2025

    • 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
      •71•749•15•1•Updated Dec 30, 2024Dec 30, 2024

    • READ-ME

      Public
      [NeurIPS2024] "Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design", Ruisi Cai, Yeonju Ro, Geon-Woo Kim, Peihao Wang, Babak Ehteshami Bejnordi, Aditya Akella, Zhangyang Wang
      Python
      •2•14•0•0•Updated Dec 16, 2024Dec 16, 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 Dec 2, 2024Dec 2, 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
      •19•196•5•0•Updated Oct 16, 2024Oct 16, 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•18•3•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
      •7•139•12•0•Updated Sep 4, 2024Sep 4, 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•78•4•0•Updated Aug 25, 2024Aug 25, 2024