TungChintao / FlowCutLinks
Official repository for “FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models”
☆21Updated last month
Alternatives and similar repositories for FlowCut
Users that are interested in FlowCut are comparing it to the libraries listed below
Sorting:
- cliptrase☆43Updated last year
- [ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models☆45Updated 6 months ago
- [ICCV25 Oral] Token Activation Map to Visually Explain Multimodal LLMs☆63Updated 3 weeks ago
- ☆38Updated last month
- The official implementation of "PixelThink: Towards Efficient Chain-of-Pixel Reasoning" (arXiv 2025)☆36Updated 3 months ago
- [CVPR 2025] Official PyTorch Implementation of GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmenta…☆49Updated 2 months ago
- [ECCV2024] ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference☆87Updated 5 months ago
- [CVPR'25] 🌟🌟 EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering☆37Updated 2 months ago
- [NeurIPS 2024 Oral] RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation☆18Updated 8 months ago
- Code and dataset link for "DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World"☆100Updated last month
- Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation☆54Updated 3 months ago
- Official implementation for the paper"Towards Understanding How Knowledge Evolves in Large Vision-Language Models"☆17Updated 4 months ago
- [NeurIPS 2024] Official PyTorch implementation of LoTLIP: Improving Language-Image Pre-training for Long Text Understanding☆43Updated 7 months ago
- ☆30Updated last year
- [ICCV 2025] Official code for paper: Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs☆25Updated 2 months ago
- [LLaVA-Video-R1]✨First Adaptation of R1 to LLaVA-Video (2025-03-18)☆30Updated 3 months ago
- [CVPR 2025 Highlight] Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding☆27Updated this week
- Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better☆37Updated 2 months ago
- [ICLR'25] Reconstructive Visual Instruction Tuning☆105Updated 4 months ago
- Official implementation of ResCLIP: Residual Attention for Training-free Dense Vision-language Inference☆43Updated 5 months ago
- [MM2024 Oral] 3D-GRES: Generalized 3D Referring Expression Segmentation☆38Updated 8 months ago
- Official repository of the paper "High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation"☆40Updated 5 months ago
- [NIPS24] Official Implementation of Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation☆19Updated 10 months ago
- ☆105Updated 5 months ago
- [CVPR 2025] Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training☆80Updated last month
- [IJCV 2024]☆16Updated 9 months ago
- [ICCV 2025] MOVE: Motion-Guided Few-Shot Video Object Segmentation☆20Updated last month
- [CVPR2025] FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression☆49Updated 6 months ago
- [ICCV 2025 Oral] Official implementation of Learning Streaming Video Representation via Multitask Training.☆40Updated 3 weeks ago
- The official repository of our paper "Reinforcing Video Reasoning with Focused Thinking"☆22Updated 2 months ago