Towards Efficient Multimodal Large Language Models: A Survey on Token Compression
☆212Jun 29, 2026Updated 3 weeks ago
Alternatives and similar repositories for MLLM-Token-Compression
Users that are interested in MLLM-Token-Compression are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [TMLR 2026] Survey: https://arxiv.org/pdf/2507.20198☆371May 29, 2026Updated last month
- A paper list of some recent works about Token Compress for Vit and VLM☆939Updated this week
- A collection of token reduction (token pruning, merging, clustering, etc.) techniques for ML/AI☆486Updated this week
- [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models☆86Apr 16, 2026Updated 3 months ago
- [CVPR 2026] OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models☆99Apr 20, 2026Updated 3 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- [CVPR 2026] Accelerating Streaming Video Large Language Models via Hierarchical Token Compression☆70Jun 8, 2026Updated last month
- [NeurIPS 2025] HoliTom: Holistic Token Merging for Fast Video Large Language Models☆84Oct 10, 2025Updated 9 months ago
- [ICLR 2026 Oral] FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging☆111Apr 30, 2026Updated 2 months ago
- [NeurIPS 2025] FastVID: Dynamic Density Pruning for Fast Video Large Language Models☆37Nov 10, 2025Updated 8 months ago
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆121Oct 12, 2025Updated 9 months ago
- [ICLR 2026] Official code repository for "⚡️VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration"☆54Jun 17, 2026Updated last month
- [ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videos☆132Jun 29, 2026Updated 3 weeks ago
- 📚 A curated collection of papers and open-source code repositories dedicated to the application of Vision-Language Models (VLMs) for str…☆188Jun 10, 2026Updated last month
- DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference☆25May 21, 2026Updated 2 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Tempo: Small Vision-Language Models are Smart Compressors for Long Video Understanding (ECCV 2026)☆76Jun 29, 2026Updated 3 weeks ago
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.☆105Sep 20, 2025Updated 10 months ago
- [NeurIPS 2025] Official repository for “FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models”☆32Dec 9, 2025Updated 7 months ago
- [Neurips’25] Code for the paper "Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization"☆31Sep 25, 2025Updated 9 months ago
- Latest Papers, Codes and Datasets on VTG-LLMs.☆95Jul 12, 2026Updated last week
- VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs☆63Mar 24, 2026Updated 3 months ago
- Code and data for VTCBench, a VLM benchmark for long-context understanding capabilities under vision-text compression paradigm.☆27Mar 16, 2026Updated 4 months ago
- [NeurIPS 2025] AutoPrune, a general pruning method for LLM/VLM/VLA☆20Oct 7, 2025Updated 9 months ago
- Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence☆385Jun 20, 2026Updated last month
- 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.
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models☆80Jul 14, 2025Updated last year
- A simple video streaming baseline that outperforms SOTAs.☆148May 1, 2026Updated 2 months ago
- [EMNLP 2025 Main] Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models☆127May 14, 2026Updated 2 months ago
- [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…☆592Jan 4, 2025Updated last year
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆266Dec 22, 2025Updated 6 months ago
- ☆26Mar 5, 2026Updated 4 months ago
- [CVPR 2026] AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition☆40Apr 27, 2026Updated 2 months ago
- [CVPR 2026] Official repository for "UniComp: Rethinking Video Compression Through Informational Uniqueness"☆27Feb 22, 2026Updated 4 months ago
- 🔥This is a repository of paper list for streaming LLMs/MLLMs.☆24Apr 19, 2026Updated 3 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.
- Fully Open Framework for Democratized Multimodal Training☆1,143Updated this week
- ☆17Apr 5, 2026Updated 3 months ago
- ☆17Mar 1, 2026Updated 4 months ago
- Multi-step reasoning MLLM☆25Mar 8, 2026Updated 4 months ago
- [NeurIPS 2025] Scaling Language-centric Omnimodal Representation Learning☆47Apr 13, 2026Updated 3 months ago
- Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual in…☆1,492Mar 9, 2026Updated 4 months ago
- [CVPR 2024] TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding☆425May 8, 2025Updated last year