Beyond Saying Less: Fine-Grained Alignment for Informative and Faithful Vision-Language Models
cs.CV
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Hallucination of Multimodal Large Language Models: A Survey
- Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations
- A Survey on Hallucination in Large Vision-Language Models
- Understanding R1-Zero-Like Training: A Critical Perspective
- Visual Hallucination: Definition, Quantification, and Prescriptive Remediations
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
- Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
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