📚 Collection of token-level model compression resources.
☆203Sep 3, 2025Updated last year
Alternatives and similar repositories for Awesome-Token-level-Model-Compression
Users that are interested in Awesome-Token-level-Model-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:
- [AAAI 2026] Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models☆43Jan 27, 2026Updated 7 months ago
- 📚 Collection of awesome generation acceleration resources.☆404Jul 7, 2025Updated last year
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆122Oct 12, 2025Updated 10 months ago
- A paper list of some recent works about Token Compress for Vit and VLM☆951Aug 31, 2026Updated last week
- [CVPR 2026] Variation-aware Vision Token Dropping for Faster Large Vision-Language Models☆35May 27, 2026Updated 3 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆38Jan 8, 2025Updated last year
- (ICLR 2026 🔥) Code for "The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs"☆79Feb 9, 2026Updated 6 months ago
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆223Mar 14, 2025Updated last year
- [EMNLP 2025 Main] Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models☆131May 14, 2026Updated 3 months ago
- [ICME 2024 Oral] DARA: Domain- and Relation-aware Adapters Make Parameter-efficient Tuning for Visual Grounding☆22Feb 26, 2025Updated last year
- Official repository for VisionZip (CVPR 2025)☆446Jul 21, 2025Updated last year
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆116Nov 22, 2025Updated 9 months ago
- Official Implementation of Paper FOLDER (ICCV2025) and Turbo (ECCV2024)☆15Jun 27, 2025Updated last year
- [AAAI-2025] The offical code for SiTo （Similarity-based Token Pruning for Stable Diffusion Models）☆47Jun 2, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆415Mar 2, 2026Updated 6 months ago
- ☆36Jun 3, 2025Updated last year
- (ToCa-v2) A New version of ToCa，with faster speed and better acceleration!☆42Mar 13, 2025Updated last year
- [NeurIPS 2025] HoliTom: Holistic Token Merging for Fast Video Large Language Models☆84Oct 10, 2025Updated 10 months ago
- Fully Open-source Multimodal Language Models for Science Discovery☆167Mar 20, 2026Updated 5 months ago
- [ICML'25][TPAMI'26] Official implementation of paper "SparseVLM" and "SparseVLM+".☆276Jul 30, 2026Updated last month
- [ICASSP 2024] VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders☆17Feb 11, 2025Updated last year
- (NeurIPS 2025 🔥) Official implementation for "Efficient Multi-modal Large Language Models via Progressive Consistency Distillation"☆49Feb 11, 2026Updated 6 months ago
- This is the open-source code for TokenCarve.☆25Jan 23, 2026Updated 7 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models☆88Apr 16, 2026Updated 4 months ago
- [CVPR 2026] Accelerating Streaming Video Large Language Models via Hierarchical Token Compression☆75Jun 8, 2026Updated 2 months ago
- Official PyTorch code for ICLR 2025 paper "Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models"☆23Mar 4, 2025Updated last year
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.☆108Sep 20, 2025Updated 11 months ago
- [CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models☆60Jan 30, 2026Updated 7 months ago
- Use Hermes Agent as the control plane for local coding agents like Codex, Kimi Code, Claude Code, OpenCode, and Gemini CLI.☆38Jul 22, 2026Updated last month
- [CVPR 2026] OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models☆108Apr 20, 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 4 months ago
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"☆65Oct 9, 2025Updated 10 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Code release for VTW (AAAI 2025 Oral)☆66Nov 4, 2025Updated 10 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆214May 1, 2026Updated 4 months ago
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆77Jan 13, 2026Updated 7 months ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆90Oct 26, 2025Updated 10 months ago
- [TMLR 2026] Survey: https://arxiv.org/pdf/2507.20198☆387Jul 27, 2026Updated last month
- [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…☆595Jan 4, 2025Updated last year
- [ICLR 2026] Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models☆31Mar 21, 2026Updated 5 months ago