A squared Safe: Counterfactual Evidence-Aligned Adaptive Agent Collaboration for Safe and Effective Visual Question Answering
cs.CV
Submitted: 2026-09-21
Updated: 2026-09-21
Terminology
Sources
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model
- Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
- Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
- SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
- Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering
- Qwen3-VL Technical Report
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