Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes
cs.CV, cs.HC
Submitted: 2026-10-04
Updated: 2026-10-10
Comments: 14 pages, 7 figures
Code: https://github.com/GuanRunwei/RoadSceneVQA-G
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
- Qwen2.5-VL Technical Report
- Qwen3-VL Technical Report
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning
- VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
- DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes
- SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards
- Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
- MiniCPM-V: A GPT-4V Level MLLM on Your Phone
- DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
- MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
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