RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models
cs.CV, cs.AI
Submitted: 2026-09-02
Updated: 2026-09-02
Code: https://github.com/canjie-liu/RVSD
Terminology
Sources
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Hallucination of Multimodal Large Language Models: A Survey
- Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
- PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
- MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction
- AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
- ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models
- A Survey on Hallucination in Large Vision-Language Models
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