LaVi-Lab / AIMLinks
[ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"
☆34Updated last month
Alternatives and similar repositories for AIM
Users that are interested in AIM are comparing it to the libraries listed below
Sorting:
- FreeVA: Offline MLLM as Training-Free Video Assistant☆60Updated last year
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆37Updated 5 months ago
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆77Updated last year
- The official repository for ACL2025 paper "PruneVid: Visual Token Pruning for Efficient Video Large Language Models".☆50Updated 2 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆40Updated 3 months ago
- Code for "AVG-LLaVA: A Multimodal Large Model with Adaptive Visual Granularity"☆30Updated 9 months ago
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models☆63Updated 3 weeks ago
- 🚀 Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models☆30Updated 2 weeks ago
- Official repository of "CoMP: Continual Multimodal Pre-training for Vision Foundation Models"☆30Updated 4 months ago
- [ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model☆46Updated 8 months ago
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆65Updated last month
- [NeurIPS'24] Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment☆57Updated 10 months ago
- Official implement of MIA-DPO☆62Updated 6 months ago
- ☆43Updated 8 months ago
- ☆45Updated 7 months ago
- (ICLR 2025 Spotlight) Official code repository for Interleaved Scene Graph.☆27Updated 6 months ago
- ☆54Updated 3 months ago
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆87Updated 3 months ago
- PyTorch code for "Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training"☆35Updated last year
- [CVPR2025] Code Release of F-LMM: Grounding Frozen Large Multimodal Models☆100Updated 2 months ago
- Emerging Pixel Grounding in Large Multimodal Models Without Grounding Supervision☆41Updated 4 months ago
- VideoNIAH: A Flexible Synthetic Method for Benchmarking Video MLLMs☆48Updated 4 months ago
- Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency☆47Updated 2 months ago
- Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning☆56Updated 2 months ago
- [CVPR 2025] Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention☆41Updated last year
- [EMNLP'23] The official GitHub page for ''Evaluating Object Hallucination in Large Vision-Language Models''☆87Updated last year
- ☆31Updated last year
- Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding☆36Updated 4 months ago
- [ICCV 2025] Dynamic-VLM☆23Updated 7 months ago
- Official repository for CoMM Dataset☆45Updated 7 months ago