BIT-DA / ABSLinks
[ICML2025] Official Code of From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection
☆24Updated 4 months ago
Alternatives and similar repositories for ABS
Users that are interested in ABS are comparing it to the libraries listed below
Sorting:
- [ICML 2025] This is the official PyTorch implementation of "🎵 HarmoniCa: Harmonizing Training and Inference for Better Feature Caching i…☆43Updated 3 months ago
- This repository contains the code for our ICML 2025 paper——LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection🎉☆24Updated 5 months ago
- [NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient☆59Updated last month
- 🚀 Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models☆36Updated last week
- Dimple, the first Discrete Diffusion Multimodal Large Language Model☆108Updated 3 months ago
- [ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models☆65Updated 8 months ago
- [CVPR 2025] VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification☆39Updated 7 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆35Updated 9 months ago
- ☆58Updated 5 months ago
- 🚀 Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models☆33Updated 3 months ago
- [NeurIPS 2025 Spotlight] Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning☆69Updated last month
- a training-free approach to accelerate ViTs and VLMs by pruning redundant tokens based on similarity☆39Updated 5 months ago
- TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation☆227Updated 2 months ago
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'☆195Updated 3 months ago
- Official code repo for our work "Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models"☆50Updated 4 months ago
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆180Updated 4 months ago
- Data distillation benchmark☆68Updated 4 months ago
- [CVPR 2025 (Oral)] Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key☆84Updated last month
- ☆27Updated 8 months ago
- Official repository of the paper "A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models"☆74Updated last month
- [CVPR 2025] Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation☆69Updated last month
- ☆22Updated 2 months ago
- [ICCV 2025] ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models☆40Updated 3 months ago
- [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models☆51Updated 5 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆95Updated 4 months ago
- (ArXiv25) Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning☆58Updated last month
- Code for the paper "AsFT: Anchoring Safety During LLM Fune-Tuning Within Narrow Safety Basin".☆30Updated 3 months ago
- ☆125Updated 7 months ago
- [ECCV 2024] API: Attention Prompting on Image for Large Vision-Language Models☆105Updated last year
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆84Updated 2 weeks ago