Alternatives and similar repositories for PACT

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

• Gumpest / SparseVLMs
  [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" and "Sp…
  ☆217Updated 2 weeks ago
• Theia-4869 / FasterVLM
  Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.
  ☆101Updated 6 months ago
• Cooperx521 / PyramidDrop
  (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
  ☆135Updated 10 months ago
• shufangxun / LLaVA-MoD
  [ICLR 2025] LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation
  ☆218Updated 9 months ago
• KD-TAO / DyCoke
  [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
  ☆95Updated last month
• vbdi / divprune
  [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
  ☆63Updated last month
• liuting20 / MustDrop
  Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
  ☆36Updated 11 months ago
• xuyang-liu16 / VidCom2
  [EMNLP 2025 Main] Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
  ☆47Updated this week
• ywh187 / FitPrune
  ☆62Updated 8 months ago
• seilk / VisAttnSink
  [ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models
  ☆82Updated 10 months ago
• Fantasyele / LLaVA-KD
  [ICCV 2025] Official implementation of LLaVA-KD: A Framework of Distilling Multimodal Large Language Models
  ☆119Updated 2 months ago
• Theia-4869 / CDPruner
  [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.
  ☆82Updated 3 months ago
• double125 / MADTP
  MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer
  ☆49Updated last year
• ncTimTang / AKS
  [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding
  ☆157Updated 2 weeks ago
• ZichenWen1 / DART
  [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"
  ☆97Updated 2 months ago
• lzhxmu / VTW
  Code release for VTW (AAAI 2025 Oral)
  ☆65Updated 2 months ago
• yu-rp / VisualPerceptionToken
  ☆132Updated 9 months ago
• 42Shawn / LLaVA-PruMerge
  LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
  ☆158Updated 3 months ago
• thu-nics / FrameFusion
  [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"
  ☆67Updated last month
• mrwu-mac / ControlMLLM
  [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'
  ☆202Updated 5 months ago
• cokeshao / Awesome-Multimodal-Token-Compression
  Survey: https://arxiv.org/pdf/2507.20198
  ☆262Updated 2 weeks 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'
  ☆311Updated 8 months ago
• cokeshao / HoliTom
  [NeurIPS'25] HoliTom: Holistic Token Merging for Fast Video Large Language Models
  ☆68Updated 2 months ago
• JinXins / Awesome-Token-Merge-for-MLLMs
  A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.
  ☆79Updated 2 months ago
• PKU-ICST-MIPL / DyFo_CVPR2025
  ☆101Updated 4 months ago
• NUS-HPC-AI-Lab / Dynamic-Tuning
  The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"
  ☆52Updated last year
• xmed-lab / TAM
  [ICCV25 Oral] Token Activation Map to Visually Explain Multimodal LLMs
  ☆148Updated 3 weeks ago
• NUS-HPC-AI-Lab / SGL
  ☆28Updated 10 months ago
• Adlith / MoE-Jetpack
  [NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
  ☆133Updated last year
• mengchuang123 / VASparse-github
  [CVPR 2025] VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification
  ☆48Updated 9 months ago