Alternatives and similar repositories for SparseVLMs

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

• Theia-4869 / FasterVLM
  Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.
  ☆84Updated last month
• Cooperx521 / PyramidDrop
  (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
  ☆118Updated 5 months ago
• 42Shawn / LLaVA-PruMerge
  LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
  ☆142Updated last month
• ZichenWen1 / DART
  [EMNLP 2025 main] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"
  ☆65Updated this week
• ywh187 / FitPrune
  ☆54Updated 3 months ago
• JinXins / Awesome-Token-Merge-for-MLLMs
  A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.
  ☆69Updated 7 months ago
• KD-TAO / DyCoke
  [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
  ☆69Updated last month
• lzhxmu / VTW
  Code release for VTW (AAAI 2025 Oral)
  ☆48Updated last month
• ChangyuanWang17 / QVLM
  [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.
  ☆79Updated 7 months ago
• thu-nics / FrameFusion
  [ICCV'25] The official code implementation of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Langua…
  ☆53Updated last week
• liuting20 / MustDrop
  Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
  ☆34Updated 7 months ago
• cokeshao / Awesome-Multimodal-Token-Compression
  Survey: https://arxiv.org/pdf/2507.20198
  ☆96Updated last week
• xuyang-liu16 / Awesome-Token-level-Model-Compression
  📚 Collection of token-level model compression resources.
  ☆151Updated 2 weeks ago
• double125 / MADTP
  MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer
  ☆46Updated 11 months ago
• yu-rp / VisualPerceptionToken
  ☆101Updated 5 months ago
• Theia-4869 / CDPruner
  Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.
  ☆49Updated last month
• dvlab-research / VisionZip
  Official repository for VisionZip (CVPR 2025)
  ☆337Updated last month
• ncTimTang / AKS
  [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding
  ☆94Updated last week
• Osilly / dynamic_llava
  [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…
  ☆51Updated 8 months ago
• MCG-NJU / p-MoD
  [ICCV 2025] p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
  ☆42Updated last month
• Yxxxb / VoCo-LLaMA
  [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".
  ☆184Updated 2 months ago
• MAC-AutoML / QuoTA
  This is the official implementation of our paper "QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehens…
  ☆73Updated 3 months ago
• Video-R1 / Awesome-Multimodal-Reasoning
  Collections of Papers and Projects for Multimodal Reasoning.
  ☆105Updated 3 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'
  ☆247Updated 4 months ago
• Adlith / MoE-Jetpack
  [NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
  ☆129Updated 9 months ago
• vbdi / divprune
  [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
  ☆41Updated 2 months ago
• shufangxun / LLaVA-MoD
  [ICLR 2025] LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation
  ☆192Updated 4 months ago
• mrwu-mac / ControlMLLM
  [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'
  ☆188Updated last month
• SUSTechBruce / LOOK-M
  [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…
  ☆98Updated 9 months ago
• xuyang-liu16 / VidCom2
  🚀 Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
  ☆29Updated 2 months ago