Answer Correction with Verifiable Rewards: A Gemma-Family Study of Multi-View Driving QA
cs.CV, cs.LG
Submitted: 2026-10-31
Updated: 2026-11-03
Terminology
Sources
- A Survey on Multimodal Large Language Models for Autonomous Driving
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- GAIA-1: A Generative World Model for Autonomous Driving
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs