LaVi-Lab / AIMLinks
[ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"
☆50Updated 3 months ago
Alternatives and similar repositories for AIM
Users that are interested in AIM are comparing it to the libraries listed below
Sorting:
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆95Updated last month
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆139Updated 10 months ago
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆41Updated 2 months ago
- [CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection☆132Updated 5 months ago
- [EMNLP 2025 Main] Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models☆50Updated this week
- [ACL 2025] PruneVid: Visual Token Pruning for Efficient Video Large Language Models☆65Updated 8 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆37Updated last year
- ☆64Updated 8 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆159Updated 3 months ago
- OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models☆47Updated last month
- [AAAI 2026] Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models☆37Updated last month
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆44Updated 9 months ago
- Official implement of MIA-DPO☆70Updated 11 months ago
- [Neurips 24' D&B] Official Dataloader and Evaluation Scripts for LongVideoBench.☆112Updated last year
- [ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videos☆108Updated last month
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models☆76Updated 6 months ago
- Code for "AVG-LLaVA: A Multimodal Large Model with Adaptive Visual Granularity"☆33Updated last year
- [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models☆63Updated last month
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆158Updated 3 weeks ago
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆84Updated 2 months ago
- Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding☆38Updated 10 months ago
- [NeurIPS'25] HoliTom: Holistic Token Merging for Fast Video Large Language Models☆68Updated 3 months ago
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models☆77Updated last year
- [ICLR2025] MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models☆93Updated last year
- [CVPR 2025] OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?☆113Updated 5 months ago
- FreeVA: Offline MLLM as Training-Free Video Assistant☆68Updated last year
- [NeurIPS 2024] Visual Perception by Large Language Model’s Weights☆55Updated 9 months ago
- Official PyTorch Code of ReKV (ICLR'25)☆88Updated 2 months ago
- Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency☆60Updated 7 months ago
- [ICCV 2025] p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay☆43Updated 6 months ago