Locating and Repairing Domain Shift in VLM Trajectory Planning
cs.CV, cs.RO
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/ZhihongCui/MoLaRx
Terminology
Sources
- Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Driving
- Understanding intermediate layers using linear classifier probes
- LFM2 Technical Report
- PaliGemma: A versatile 3B VLM for transfer
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
- Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
- GPT-Driver: Learning to Drive with GPT
- Mass-Editing Memory in a Transformer
- Zero-Shot Cross-City Generalization in End-to-End Autonomous Driving: Self-Supervised versus Supervised Representations
- LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving
- Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers
- DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
- LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset
- Tent: Fully Test-time Adaptation by Entropy Minimization
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting
- WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios
- RoCA: Robust Cross-Domain End-to-End 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