hasanar1f / HiRED
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.
☆13Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for HiRED
- ☆29Updated 3 weeks ago
- ☆30Updated last month
- The official GitHub page for ''What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Ins…☆18Updated last year
- Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning☆17Updated 2 months ago
- [ICCV2023] Official code for "VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control"☆52Updated last year
- [ICML 2024] Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning☆43Updated 6 months ago
- [ACL 2023] PuMer: Pruning and Merging Tokens for Efficient Vision Language Models☆28Updated last month
- ☆35Updated last month
- Adapting LLaMA Decoder to Vision Transformer☆27Updated 5 months ago
- HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data (Accepted by CVPR 2024)☆41Updated 3 months ago
- [NeurIPS'24] Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment☆48Updated last month
- The official code of the paper "PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction".☆42Updated last week
- ☆84Updated 11 months ago
- CLIP-MoE: Mixture of Experts for CLIP☆17Updated last month
- MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models☆51Updated last month
- [EMNLP 2024] Official code for "Beyond Embeddings: The Promise of Visual Table in Multi-Modal Models"☆14Updated 3 weeks ago
- ☆17Updated 8 months ago
- Official code for "pi-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation", ICML 2023.☆32Updated last year
- Code for paper "AGLA: Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention"☆15Updated 3 months ago
- Emerging Pixel Grounding in Large Multimodal Models Without Grounding Supervision☆19Updated 3 weeks ago
- Implementation of "VL-Mamba: Exploring State Space Models for Multimodal Learning"☆78Updated 7 months ago
- The codebase for our EMNLP24 paper: Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Mo…☆52Updated last month
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆57Updated 5 months ago
- This is the official repo for the incoming work: ByteVideoLLM☆12Updated last week
- [ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs☆64Updated this week
- ✨✨ MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?☆77Updated last month
- Making LLaVA Tiny via MoE-Knowledge Distillation☆55Updated 2 weeks ago
- TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models☆18Updated this week
- ☆24Updated last month
- [NeurIPS-24] This is the official implementation of the paper "DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effect…☆32Updated 4 months ago