From Foundation VLM to Versatile Driving VLM: A Triplet Incremental Training Approach
cs.CV, cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
- Qwen3-VL Technical Report
- GPT-4o System Card
- LLM4Drive: A Survey of Large Language Models for Autonomous Driving
- DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
- ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
- VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving
- EMMA: End-to-End Multimodal Model for Autonomous Driving
- WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language Model
- DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving
- VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision
- AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
- Distilling the Knowledge in a Neural Network
- DRAMA: An Efficient End-to-end Motion Planner for Autonomous Driving with Mamba
- Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation
- AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving
- Decoupled Weight Decay Regularization
- Real-Time Object Detection Meets DINOv3
- iPad: Iterative Proposal-centric 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