Alternatives and similar repositories for saint

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

• Theia-4869 / VisPruner
  [ICCV 2025] Official code for paper: Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
  ☆68Updated 7 months ago
• Theia-4869 / FasterVLM
  Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.
  ☆106Updated 7 months ago
• Gumpest / SparseVLMs
  [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" and "Sp…
  ☆237Updated last month
• NUS-HPC-AI-Lab / SGL
  ☆29Updated 11 months ago
• liuting20 / MustDrop
  Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
  ☆37Updated last year
• ywh187 / FitPrune
  ☆64Updated 3 weeks ago
• hasanar1f / HiRED
  [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…
  ☆44Updated 9 months ago
• ZichenWen1 / DART
  [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"
  ☆103Updated 4 months ago
• Adlith / MoE-Jetpack
  [NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
  ☆134Updated last year
• orailix / PACT
  [CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models
  ☆55Updated 2 weeks ago
• xuyang-liu16 / VidCom2
  [EMNLP 2025 Main] Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
  ☆61Updated last week
• OpenSparseLLMs / CLIP-MoE
  CLIP-MoE: Mixture of Experts for CLIP
  ☆55Updated last year
• xuyang-liu16 / Awesome-Token-level-Model-Compression
  📚 Collection of token-level model compression resources.
  ☆190Updated 5 months ago
• JieShibo / MoLE
  [ICML 2025 Oral] Mixture of Lookup Experts
  ☆70Updated 2 months ago
• scale-lab / MTLoRA
  The official implementation for MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning (CVPR '24)
  ☆69Updated 7 months ago
• ChangyuanWang17 / QVLM
  [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.
  ☆95Updated last year
• MPSC-UMBC / Efficient-Vision-Language-Models-A-Survey
  [2025] Efficient Vision Language Models: A Survey
  ☆47Updated 6 months ago
• czg1225 / VeriThinker
  [NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient
  ☆64Updated 4 months ago
• sdc17 / CrossGET
  [ICML 2024] CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
  ☆34Updated last year
• vbdi / divprune
  [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
  ☆65Updated 2 months ago
• yu-rp / Dimple
  Dimple, the first Discrete Diffusion Multimodal Large Language Model
  ☆114Updated 7 months ago
• KD-TAO / OmniZip
  OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
  ☆51Updated last week
• 42Shawn / LLaVA-PruMerge
  LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
  ☆163Updated 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
• ZichenWen1 / EPIC
  (NeurIPS 2025 🔥) Official implementation for "Efficient Multi-modal Large Language Models via Progressive Consistency Distillation"
  ☆40Updated 2 months ago
• Cooperx521 / PyramidDrop
  (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
  ☆141Updated 11 months ago
• KD-TAO / DyCoke
  [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
  ☆99Updated 2 months ago
• lzhxmu / VTW
  Code release for VTW (AAAI 2025 Oral)
  ☆64Updated 3 months ago
• techmonsterwang / iLLaMA
  Adapting LLaMA Decoder to Vision Transformer
  ☆30Updated last year
• LaVi-Lab / AIM
  [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"
  ☆54Updated 4 months ago