Osilly / dynamic_llava
[ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification".
☆28Updated 4 months ago
Alternatives and similar repositories for dynamic_llava:
Users that are interested in dynamic_llava are comparing it to the libraries listed below
- Code release for VTW (AAAI 2025) Oral☆34Updated 2 months ago
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆92Updated 5 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆28Updated 2 months ago
- ☆41Updated 3 months ago
- ☆69Updated 10 months ago
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆51Updated 4 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆71Updated 5 months ago
- The official repository for the paper "Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark"☆48Updated 2 weeks ago
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆37Updated 4 months ago
- A Self-Training Framework for Vision-Language Reasoning☆75Updated 2 months ago
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆71Updated 10 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆89Updated last month
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)☆45Updated 5 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆123Updated 10 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆36Updated 9 months ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆47Updated 3 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆26Updated 3 months ago
- ☆71Updated 3 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆66Updated 4 months ago
- HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data (Accepted by CVPR 2024)☆45Updated 8 months ago
- Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal …☆46Updated last month
- MoCLE (First MLLM with MoE for instruction customization and generalization!) (https://arxiv.org/abs/2312.12379)☆35Updated last year
- GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning☆30Updated this week
- VideoNIAH: A Flexible Synthetic Method for Benchmarking Video MLLMs☆46Updated last month
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆62Updated 2 months ago
- Recent Advances on MLLM's Reasoning Ability☆24Updated this week
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆35Updated 2 months ago
- ☆37Updated this week
- The codebase for our EMNLP24 paper: Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Mo…☆76Updated 2 months ago
- code for "Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization"☆54Updated 7 months ago