Alternatives and similar repositories for PACT

Users that are interested in PACT are comparing it to the libraries listed below

• ncTimTang / AKS
  [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding
  ☆66Updated last month
• Fantasyele / LLaVA-KD
  ☆78Updated 6 months ago
• mengchuang123 / VASparse-github
  [CVPR 2025] VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification
  ☆34Updated 2 months ago
• seilk / VisAttnSink
  [ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models
  ☆30Updated 3 months ago
• mrwu-mac / ControlMLLM
  [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'
  ☆174Updated last week
• Hoar012 / RAP-MLLM
  [CVPR 2025] RAP: Retrieval-Augmented Personalization
  ☆56Updated 2 weeks ago
• ywh187 / FitPrune
  ☆46Updated last month
• yu-rp / VisualPerceptionToken
  ☆84Updated 2 months ago
• Cooperx521 / PyramidDrop
  (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
  ☆105Updated 3 months ago
• double125 / MADTP
  MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer
  ☆43Updated 9 months ago
• liuting20 / Sparse-Tuning
  ☆28Updated 11 months ago
• DoubtedSteam / RoE
  The official implement of "Routing Experts: Learning to Route Dynamic Experts in Existing Multi-modal Large Language Models"
  ☆13Updated 2 months ago
• codefanw / FlashSloth
  [CVPR2025] FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression
  ☆41Updated 3 months ago
• ZhangqiJiang07 / middle_layers_indicating_hallucinations
  [CVPR 2025] Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Att…
  ☆18Updated 3 months ago
• congvvc / InstructSeg
  Official implementation of "InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models"
  ☆38Updated 3 months ago
• FeipengMa6 / VLoRA
  [NeurIPS 2024] Visual Perception by Large Language Model’s Weights
  ☆45Updated 2 months ago
• KD-TAO / DyCoke
  [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
  ☆48Updated last week
• nini0919 / DiffPNG
  [ECCV2024]The official implementation of the DiffPNG paper in PyTorch.
  ☆12Updated 7 months ago
• saccharomycetes / mllms_know
  [ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'
  ☆207Updated last month
• wusize / F-LMM
  [CVPR2025] Code Release of F-LMM: Grounding Frozen Large Multimodal Models
  ☆91Updated last week
• xuyang-liu16 / GlobalCom2
  🚀 Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
  ☆27Updated 2 weeks ago
• johncaged / OPT_Questioner
  Official PyTorch implementation of the paper "Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner"
  ☆15Updated last year
• Yxxxb / VoCo-LLaMA
  [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".
  ☆165Updated last week
• Osilly / TokenExpansion
  [CVPR 2024] The official pytorch implementation of "A General and Efficient Training for Transformer via Token Expansion".
  ☆44Updated last year
• Theia-4869 / FasterVLM
  Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.
  ☆76Updated 5 months ago
• lntzm / HICom
  [CVPR2025] Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models
  ☆12Updated last month
• Wang-Xiaodong1899 / CVPR25-MLLM-Paper-List
  🔥CVPR 2025 Multimodal Large Language Models Paper List
  ☆143Updated 2 months ago
• yvhangyang / ResCLIP
  Official implementation of ResCLIP: Residual Attention for Training-free Dense Vision-language Inference
  ☆37Updated 2 months ago
• ZichenWen1 / DART
  Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"
  ☆49Updated last month
• mbzuai-oryx / VideoGLaMM
  [CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
  ☆66Updated last month