[CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models
☆60Jan 30, 2026Updated 9 months ago
Alternatives and similar repositories for PACT
Users that are interested in PACT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models☆91Apr 16, 2026Updated 6 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆153Mar 6, 2025Updated last year
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"☆65Oct 9, 2025Updated last year
- [ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Langua…☆598Jan 4, 2025Updated last year
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆116Jun 29, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICML'25][TPAMI'26] Official implementation of paper "SparseVLM" and "SparseVLM+".☆286Jul 30, 2026Updated 3 months ago
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆122Oct 12, 2025Updated last year
- [ICCV 2025] Official code for paper: Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs☆85Jul 1, 2025Updated last year
- [ICLR 2026] The official repo of "MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs"☆47Sep 2, 2026Updated last month
- [NeurIPS 2025] Official repository for “FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models”☆34Dec 9, 2025Updated 10 months ago
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆118Nov 22, 2025Updated 11 months ago
- Official repository for VisionZip (CVPR 2025)☆460Jul 21, 2025Updated last year
- [ACL-2026 Findings] Implementation for HiPrune, a training-free visual token pruning method for VLM acceleration.☆61Apr 29, 2026Updated 6 months ago
- MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer☆51Sep 6, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning☆18Feb 27, 2026Updated 8 months ago
- A paper list of some recent works about Token Compress for Vit and VLM☆964Updated this week
- [CVPR 2026] OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning☆17May 20, 2026Updated 5 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆58Apr 18, 2025Updated last year
- Revisiting Visual Token Pruning for Vision-Language Model Acceleration☆11Jul 31, 2025Updated last year
- Research works from Tencent AI Lab regarding self-evolving agents☆99Jan 30, 2026Updated 9 months ago
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.☆112Sep 20, 2025Updated last year
- [NeurIPS 2025 🔥] Official implementation for "Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retenti…☆66Mar 5, 2026Updated 7 months ago
- ☆26Oct 31, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 😎 Awesome papers on token redundancy reduction☆14Mar 12, 2025Updated last year
- ☆29May 13, 2025Updated last year
- Learnable Semi-structured Sparsity for Vision Transformers and Diffusion Transformers☆15Feb 7, 2025Updated last year
- a training-free approach to accelerate ViTs and VLMs by pruning redundant tokens based on similarity☆44May 24, 2025Updated last year
- [CVPR '24] Official implementation of the paper "Multiflow: Shifting Towards Task-Agnostic Vision-Language Pruning".☆24Mar 7, 2025Updated last year
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…☆73Sep 18, 2025Updated last year
- This repo is the official implementation of "Stage-adaptive Token Selection for Efficient Omni-modal LLMs"☆20Oct 11, 2026Updated 2 weeks ago
- [TMLR 2026] Survey: https://arxiv.org/pdf/2507.20198☆404Jul 27, 2026Updated 3 months ago
- This is the open-source code for TokenCarve.☆25Jan 23, 2026Updated 9 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [NAACL 2025🔥] MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference☆23Jun 19, 2025Updated last year
- AFPQ code implementation☆23Nov 6, 2023Updated 2 years ago
- [NeurIPS 2025] FastVID: Dynamic Density Pruning for Fast Video Large Language Models☆39Nov 10, 2025Updated 11 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆178Nov 26, 2025Updated 11 months ago
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆81Oct 9, 2026Updated 3 weeks ago
- (AAAI 2026) First-Order Error Matters: Accurate Compensation for Quantized Large Language Models☆17Apr 16, 2026Updated 6 months ago
- [NeurIPS 2025] AutoPrune, a general pruning method for LLM/VLM/VLA☆21Oct 7, 2025Updated last year