Evaluating Video LLMs' Understanding of Corner Cases in Autonomous Driving
cs.CV, cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
- Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches
- TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
- Lost in Time: A New Temporal Benchmark for VideoLLMs
- Visually Prompted Benchmarks Are Surprisingly Fragile
- VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
- CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning
- Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving
- CrashChat: A Multimodal Large Language Model for Multitask Traffic Crash Video Analysis
- Ovis2.5 Technical Report
- HREF: Human Response-Guided Evaluation of Instruction Following in Language Models
- OpenAI GPT-5 System Card
- MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark
- Qwen3-VL Technical Report
- Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling
- Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
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