LaVi-Lab / AIMLinks
[ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"
☆54Updated 3 months ago
Alternatives and similar repositories for AIM
Users that are interested in AIM are comparing it to the libraries listed below
Sorting:
- ☆64Updated 2 weeks ago
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆96Updated 2 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆141Updated 11 months ago
- OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models☆51Updated last week
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆42Updated 3 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆37Updated last year
- [ACL 2025] PruneVid: Visual Token Pruning for Efficient Video Large Language Models☆66Updated 8 months ago
- [CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection☆134Updated 6 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆162Updated 4 months ago
- [ICCV 2025] p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay☆43Updated 7 months ago
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆84Updated 3 months ago
- Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency☆60Updated 8 months ago
- [AAAI 2026] Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models☆38Updated last week
- [ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videos☆114Updated last month
- [EMNLP 2025 Main] Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models☆60Updated this week
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models☆77Updated 6 months ago
- ☆110Updated last year
- Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning☆45Updated 7 months ago
- Official implement of MIA-DPO☆70Updated last year
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆66Updated 7 months ago
- FreeVA: Offline MLLM as Training-Free Video Assistant☆68Updated last year
- Official repository for CoMM Dataset☆49Updated last year
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆44Updated 9 months ago
- [ICCV 2025] VisRL: Intention-Driven Visual Perception via Reinforced Reasoning☆44Updated 3 months ago
- VideoNIAH: A Flexible Synthetic Method for Benchmarking Video MLLMs☆54Updated 10 months ago
- [Neurips 24' D&B] Official Dataloader and Evaluation Scripts for LongVideoBench.☆113Updated last year
- [ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs☆162Updated last year
- PyTorch Implementation of "Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Larg…☆37Updated 2 months ago
- ✨✨[AAAI 2026] This is the official implementation of our paper "QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Vi…☆77Updated 9 months ago
- [NeurIPS 2025 Spotlight] Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning☆78Updated 4 months ago