Implementation for HiPrune, a training-free visual token pruning method for VLM acceleration.
☆46Oct 29, 2025Updated 4 months ago
Alternatives and similar repositories for HiPrune
Users that are interested in HiPrune are comparing it to the libraries listed below
Sorting:
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"☆55Oct 9, 2025Updated 4 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆44Apr 18, 2025Updated 10 months ago
- The official code for the paper: LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs☆118Jul 1, 2025Updated 8 months ago
- [ICCV 2025] SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs☆82Jan 17, 2026Updated last month
- Code for "CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning"☆32Mar 26, 2025Updated 11 months ago
- Official repository of the paper "A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models"☆91Feb 13, 2026Updated 3 weeks ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆142Mar 6, 2025Updated last year
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆107Oct 12, 2025Updated 4 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…☆556Jan 4, 2025Updated last year
- Code for "AVG-LLaVA: A Multimodal Large Model with Adaptive Visual Granularity"☆33Oct 12, 2024Updated last year
- [ICCV 2025] Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs☆57Feb 2, 2026Updated last month
- "Editing Motion Graphics Video via Motion Vectorization and Transformation." SIGGRAPH Asia 2023.☆14Jan 24, 2024Updated 2 years ago
- Content classification/clustering through language processing☆25Mar 10, 2012Updated 13 years ago
- [ICCV 2025] Official code for paper: Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs☆69Jul 1, 2025Updated 8 months ago
- ☆14Apr 19, 2025Updated 10 months ago
- Social distance Monitoring using OpenCV and Yolo Object Detector☆11Jul 24, 2020Updated 5 years ago
- 😎 Awesome papers on token redundancy reduction☆11Mar 12, 2025Updated 11 months ago
- Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval (ICCV 2025 Highlight)☆20Aug 1, 2025Updated 7 months ago
- natural language processing in the browser - i18n☆10Aug 6, 2015Updated 10 years ago
- Code for the paper "Spatial-Temporal Multi-Cuts for Online Multiple-Camera Vehicle Tracking"☆15Apr 12, 2025Updated 10 months ago
- Map Optimization and Ongoing Bug-fixing mod for Cities Skylines 2☆10Dec 1, 2023Updated 2 years ago
- Code for the paper "No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations"☆12Oct 31, 2024Updated last year
- Image Tokenizer Needs Post-Training☆24Oct 4, 2025Updated 5 months ago
- odgt CrowdHuman dataset annotation to YOLO txt and Pascal VOC xml☆10Dec 1, 2020Updated 5 years ago
- See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction (NeurIPS 2025)☆26Oct 21, 2025Updated 4 months ago
- Source code for the paper: "Pantheon: Preemptible Multi-DNN Inference on Mobile Edge GPUs"☆16Apr 15, 2024Updated last year
- SparklingGraph documentation☆10Jan 7, 2020Updated 6 years ago
- 2018-2024 in-depth completion of top papers, open source code summary! (Continuous update)☆13Sep 1, 2024Updated last year
- ☆10May 12, 2018Updated 7 years ago
- ☆12Apr 2, 2024Updated last year
- 可以随机生成制定数量的车牌号，因为用到停车场的虚假数据生成，所以地区集中在一个地方。支持各类车辆的生成，只需在注释的地方修改即可。☆10May 30, 2021Updated 4 years ago
- Official Implementation for ACM MM2024 paper "VrdONE: One-stage Video Visual Relation Detection".☆11Nov 13, 2024Updated last year
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'☆204Jul 17, 2025Updated 7 months ago
- This is the open-source code for TokenCarve.☆23Jan 23, 2026Updated last month
- The official implementation of dLLM-Var☆31Nov 6, 2025Updated 4 months ago
- 2021第三届华为云人工智能大赛 · 无人车挑战杯——车道线检测模块☆12Sep 26, 2021Updated 4 years ago
- ☆14Dec 25, 2023Updated 2 years ago
- ☆10Nov 22, 2022Updated 3 years ago
- A handwritten Chemical Structure Image data set named EDU-CHEMC, which consists of totally 52,987 handwritten molecular structure images …☆14May 12, 2025Updated 9 months ago