SUSTechBruce / LOOK-MLinks
[EMNLP 2024 Findingsπ₯] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference"
β97Updated 6 months ago
Alternatives and similar repositories for LOOK-M
Users that are interested in LOOK-M are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Contβ¦β40Updated 6 months ago
- Code release for VTW (AAAI 2025) Oralβ43Updated 4 months ago
- π LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Trainingβ86Updated 6 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Modelsβ130Updated last year
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encodingβ47Updated 5 months ago
- β74Updated 11 months ago
- β77Updated 4 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cacheβ¦β72Updated this week
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.β57Updated 4 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuningβ69Updated 3 months ago
- This repo contains evaluation code for the paper "MileBench: Benchmarking MLLMs in Long Context"β34Updated 10 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visioβ¦β35Updated last month
- NoisyRollout: Reinforcing Visual Reasoning with Data Augmentationβ64Updated 2 weeks ago
- β46Updated 3 weeks ago
- β83Updated last month
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*β103Updated last week
- Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"β46Updated last month
- β100Updated last month
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concenβ¦β66Updated this week
- β99Updated last year
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.β74Updated 6 months ago
- A Self-Training Framework for Vision-Language Reasoningβ80Updated 4 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.β76Updated 5 months ago
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Modelsβ112Updated last month
- β32Updated 2 weeks ago
- β45Updated last month
- [arXiv 2025] Efficient Reasoning Models: A Surveyβ166Updated last week
- [ICLR2025 Oral] ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understandingβ84Updated 2 months ago
- β25Updated last year
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reductionβ105Updated 2 months ago