[NAACL 2025๐ฅ] MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference
โ21Jun 19, 2025Updated last year
Alternatives and similar repositories for MEDA
Users that are interested in MEDA 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 2026] Variation-aware Vision Token Dropping for Faster Large Vision-Language Modelsโ30May 27, 2026Updated last month
- [EMNLP 2024 Findings๐ฅ] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inโฆโ103Nov 9, 2024Updated last year
- pytorch-TripletSemiHardLossโ10Jan 12, 2022Updated 4 years ago
- Cross-Self KV Cache Pruning for Efficient Vision-Language Inferenceโ10Dec 15, 2024Updated last year
- Fast, memory-efficient attention column reduction (e.g., sum, mean, max)โ49Feb 10, 2026Updated 4 months ago
- End-to-end encrypted cloud storage - Proton Drive โข AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- [AAAI 2026] Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Modelsโ42Jan 27, 2026Updated 5 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visioโฆโ56Apr 18, 2025Updated last year
- [EMNLP 2025 Main] SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruningโ46Apr 16, 2026Updated 2 months ago
- Must-read papers on Fine-grained Entity Typingโ19Jul 7, 2022Updated 3 years ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Modelsโ24Oct 5, 2024Updated last year
- A comprehensive and efficient long-context model evaluation frameworkโ31Feb 25, 2026Updated 4 months ago
- Demo for advanced Java final project in 18-19 1 of Canghong Jinโ25Nov 18, 2018Updated 7 years ago
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identificationโ33Mar 30, 2025Updated last year
- โ35Jun 3, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer โข AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- โ21May 19, 2025Updated last year
- This is the open-source code for TokenCarve.โ25Jan 23, 2026Updated 5 months ago
- โ38Nov 14, 2025Updated 7 months ago
- [ICCV 2025] A Benchmark for Multi-Step Reasoning in Long Narrative Videosโ28Jun 4, 2026Updated 3 weeks ago
- CVPR2024 highlight.โ13Oct 10, 2024Updated last year
- [ICML 2025] CommVQ: Commutative Vector Quantization for KV Cache Compressionโ27Sep 2, 2025Updated 9 months ago
- ๅธธ็จ็ocrๆฐๆฎ้โ16Nov 15, 2021Updated 4 years ago
- AutoHallusion Codebase (EMNLP 2024)โ23Dec 6, 2024Updated last year
- โ16May 15, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer โข AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A lightweight cross-platform prompt manager for researchers to organize, reuse, and iterate high-quality prompts.โ48Apr 12, 2026Updated 2 months ago
- [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3โ4ร reduction in memory and 2ร decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)โ223Feb 11, 2026Updated 4 months ago
- MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Followingโ16Oct 31, 2024Updated last year
- โ47Nov 25, 2024Updated last year
- MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformerโ50Sep 6, 2024Updated last year
- ViLoMem: Agentic Learner with Grow-and-Refine Multimodal Semantic Memoryโ66Apr 21, 2026Updated 2 months ago
- [ACL '26 Findings] V-MAGE: A Game Evaluation Framework for Assessing Visual-Centric Capabilities in MLLMsโ27Apr 28, 2026Updated 2 months ago
- โ10Dec 3, 2024Updated last year
- [NeurIPS'2025] Official repository for "LiveStar: Live Streaming Assistant for Real-World Online Video Understanding"โ132Nov 25, 2025Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer โข AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)โ34Mar 7, 2025Updated last year
- โ17Sep 11, 2025Updated 9 months ago
- โ36Oct 4, 2025Updated 8 months ago
- EUV Layer Hotspot Detection Benchmark Suitโ20Mar 8, 2021Updated 5 years ago
- โ13Jul 3, 2024Updated last year
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"โ64Oct 9, 2025Updated 8 months ago
- Project Page for GaussianFormerโ24May 30, 2024Updated 2 years ago