HAFI-VLM: A Frequency Perspective for Diagnosing and Enhancing Visual Perception in Vision-Language Models
Jin Cui, Chuanchang Su, Jiayi Lu, Xinyue Long, Boran Zhao, Pengju Ren
cs.CV, cs.CL
Submitted: 2026-08-03
Comments: 11 pages, 8 figure
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen2.5-VL Technical Report
- MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding
- Beyond Compression: Quantifying Spectral Accessibility in Vision Representations
- TGIF: Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs
- AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
- Mema: Memory-Augmented Adapter for Enhanced Vision-Language Understanding
- Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
- Language-Instructed Vision Embeddings for Controllable and Generalizable Perception
- Steerable Visual Representations
- When Do We Not Need Larger Vision Models?
- Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perception
- Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models
- Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models
- VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
- Dense Connector for MLLMs
- MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
- Frequency-Aware Semantic Fusion with Gated Injection for AI-generated Image Detection
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models