Fewer Tokens, More Answers: Verifiable-Reward Tuning of an Ornith-Style VLM for Multi-View Driving QA
cs.CV, cs.CL, cs.LG
Submitted: 2026-10-31
Updated: 2026-11-03
Comments: 7 pages, 2 figures, 3 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Training Large Language Models to Reason in a Continuous Latent Space
- Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
- LLaVA-CoT: Let Vision Language Models Reason Step-by-Step
- WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving
- Leveraging Latent Visual Reasoning in Silence
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