[AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Vision-Language Models (e.g., LLaVA-Next) under a fixed token budget.
☆58Apr 18, 2025Updated last year
Alternatives and similar repositories for HiRED
Users that are interested in HiRED 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 Workshop] PAINT (Paying Attention to INformed Tokens) is a plug-and-play framework that intervenes in the self-attention of th…☆20Updated this week
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆151Mar 6, 2025Updated last year
- [ECCV 2024] FlexAttention for Efficient High-Resolution Vision-Language Models☆49Jan 8, 2025Updated last year
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆121Oct 12, 2025Updated 9 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆36Jan 8, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- [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
- [NAACL 2025🔥] MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference☆22Jun 19, 2025Updated last year
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆103Nov 9, 2024Updated last year
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆173Mar 8, 2026Updated 4 months ago
- ☆13Jun 20, 2023Updated 3 years ago
- ☆68Jan 23, 2026Updated 5 months ago
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆12Jun 18, 2024Updated 2 years ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆114Jun 29, 2025Updated last year
- [ACL-2026 Findings] Implementation for HiPrune, a training-free visual token pruning method for VLM acceleration.☆58Apr 29, 2026Updated 2 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆266Dec 22, 2025Updated 6 months ago
- [ICCV 2025] ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models☆51Jul 7, 2025Updated last year
- [CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models☆60Jan 30, 2026Updated 5 months ago
- [CVPR 2026] TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model☆17Feb 23, 2026Updated 4 months ago
- Cross-Self KV Cache Pruning for Efficient Vision-Language Inference☆10Dec 15, 2024Updated last year
- A paper list of some recent works about Token Compress for Vit and VLM☆939Updated this week
- [AAAI 2026] Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models☆42Jan 27, 2026Updated 5 months ago
- [ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videos☆132Jun 29, 2026Updated 3 weeks ago
- [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".☆205Jun 18, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- A huge dataset for Document Visual Question Answering☆24Jul 29, 2024Updated last year
- Visual Instruction Tuning for Qwen2 Base Model☆43Jun 29, 2024Updated 2 years ago
- [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models☆86Apr 16, 2026Updated 3 months ago
- The official repo for the paper "Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching"☆18Mar 17, 2025Updated last year
- [ECCV 2024] Efficient Inference of Vision Instruction-Following Models with Elastic Cache☆43Jul 26, 2024Updated last year
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"☆65Oct 9, 2025Updated 9 months 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
- [ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model☆48Nov 10, 2024Updated last year
- [CVPR 2025] PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models☆54Jun 12, 2025Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- LLaVA-UHD v3: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs☆423Jul 6, 2026Updated 2 weeks ago
- Official PyTorch implementation of the paper "Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Princ…☆43Jul 18, 2025Updated last year
- Portable auto-vectorizable n-body benchmark☆21Feb 25, 2026Updated 4 months ago
- Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."☆54Oct 19, 2024Updated last year
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆146Sep 11, 2025Updated 10 months ago
- ☆21Feb 5, 2024Updated 2 years ago
- ☆11Dec 20, 2024Updated last year