Official code for **Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity** (PruneSID)
☆14Mar 25, 2026Updated 7 months ago
Alternatives and similar repositories for PruneSID
Users that are interested in PruneSID are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ACM MM 2025] Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding☆13Jul 15, 2025Updated last year
- [CVPR 2026 🎉] Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models☆21Oct 19, 2026Updated last week
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.☆112Sep 20, 2025Updated last year
- [ICLR 2026] AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models☆32Oct 14, 2026Updated 2 weeks ago
- [NeurIPS 2025 🔥] Official implementation for "Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retenti…☆66Mar 5, 2026Updated 7 months 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.
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆122Oct 12, 2025Updated last year
- An implementation of the hallucination mitigation method "REVIS" introduced in "Sparse Latent Steering to Mitigate Object Hallucination i…☆16Feb 12, 2026Updated 8 months ago
- [ACL 2026 Main] See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video …☆32Jul 4, 2026Updated 3 months ago
- 一个基于JAVA的简易植物大战僵尸游戏的的实现☆15Dec 22, 2025Updated 10 months ago
- [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models☆91Apr 16, 2026Updated 6 months ago
- Project Page for CVPR'26: SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation.☆11Mar 29, 2026Updated 7 months ago
- [ICML 2026] CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception☆18Aug 5, 2026Updated 2 months ago
- Relabeling of the POPE benchmark☆14May 16, 2025Updated last year
- Official repo for paper: the Geometric Nature and a Free Proxy for Flow-Matching Uncertainty☆21Oct 22, 2026Updated last week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Code release for VTW (AAAI 2025 Oral)☆66Nov 4, 2025Updated 11 months ago
- ☆20Mar 20, 2026Updated 7 months ago
- This is the official repository for paper: cross-modal information flow in multimodal large language models☆45May 21, 2025Updated last year
- Official code for paper "Reasoning Fails Where Step Flow Breaks" (ACL 2026)☆19Apr 19, 2026Updated 6 months ago
- [ICLR 2026] "Multi-Agent Debate with Memory Masking"☆14Apr 21, 2026Updated 6 months ago
- ☆13Dec 9, 2025Updated 10 months ago
- ☆18May 16, 2026Updated 5 months ago
- QA and summarization over long-context documents☆12Mar 16, 2025Updated last year
- [ICCV 2025] ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models☆53Jul 7, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆12May 19, 2025Updated last year
- [ACL 2025 Main] InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning☆13Jun 3, 2025Updated last year
- [ICLR' 2026] Official code for "COMI: Coarse-to-fine Context Compression via Marginal Information Gain"☆13Jun 29, 2026Updated 4 months ago
- [ACL2026 Main] Data & Code of "Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods"☆37Apr 9, 2026Updated 6 months ago
- Revisiting Visual Token Pruning for Vision-Language Model Acceleration☆11Jul 31, 2025Updated last year
- ☆15Apr 27, 2026Updated 6 months ago
- [ICCV 2021] Multimodal Knowledge Expansion☆10Aug 28, 2021Updated 5 years ago
- ☆12Feb 13, 2026Updated 8 months ago
- ☆11Mar 19, 2026Updated 7 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆11Jul 26, 2024Updated 2 years ago
- [ICCV 2025] Implementation of "TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning"☆12Jul 30, 2025Updated last year
- ☆11Sep 30, 2024Updated 2 years ago
- yelp(美版大众点评)点评数据分析与推荐项目后端仓库，是集成了大数据分析及可视化，以及大数据应用开发的WebApp应用.☆15Jul 20, 2024Updated 2 years ago
- [TCSVT 2024] Official implementation of the paper: Benchmarking Micro-action Recognition: Dataset, Methods, and Applications☆55Aug 27, 2026Updated 2 months ago
- ☆16Nov 11, 2025Updated 11 months ago
- [ACL'25 Findings] ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing☆12Aug 11, 2025Updated last year