# EVLA: An Electro-Aware Multimodal Assistant for Physically-Grounded Driving Reasoning and Control

arXiv: https://arxiv.org/abs/2606.28938 · HTML: https://mlsanity.com/paper/2606.28938/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning.
- Builds on 40 of its 89 references that are in the map.
- First posted on arXiv 27 Jun 2026.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)
- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)
- End-to-end autonomous driving / [Reasoning VLA and VLM driving policies](https://mlsanity.com/driving/reasoning-vla-and-vlm-driving-policies/)

## Builds on (most cited first, 30 of 40)

- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding](https://mlsanity.com/paper/2510.06308/) (2025)
- [ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding](https://mlsanity.com/paper/2506.01300/) (2025)
- [Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges](https://mlsanity.com/paper/2409.02387/) (2024)
- [Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling](https://mlsanity.com/paper/2507.17801/) (2025)
- [Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware Inversion](https://mlsanity.com/paper/2501.04606/) (2025)
- [A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks](https://mlsanity.com/paper/2411.06284/) (2024)
- [Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks](https://mlsanity.com/paper/2409.08087/) (2024)
- [GUI Agents for Continual Game Generation](https://mlsanity.com/paper/2605.28258/) (2026)
- [Large Language Model Benchmarks in Medical Tasks](https://mlsanity.com/paper/2410.21348/) (2024)
- [MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems](https://mlsanity.com/paper/2605.25002/) (2026)
- [MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs](https://mlsanity.com/paper/2511.14159/) (2025)
- [PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference](https://mlsanity.com/paper/2509.04467/) (2025)
- [Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models](https://mlsanity.com/paper/2509.09119/) (2025)
- [TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts](https://mlsanity.com/paper/2512.22748/) (2025)
- [HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance](https://mlsanity.com/paper/2510.02630/) (2025)
- [Multi-Agent Medical Decision Consensus Matrix System: An Intelligent Collaborative Framework for Oncology MDT Consultations](https://mlsanity.com/paper/2512.14321/) (2025)
- [SuperFlow: Training Flow Matching Models with RL on the Fly](https://mlsanity.com/paper/2512.17951/) (2025)
- [STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning](https://mlsanity.com/paper/2606.15866/) (2026)
- [TrimTokenator: Towards Adaptive Visual Token Pruning for Large Multimodal Models](https://mlsanity.com/paper/2509.00320/) (2025)
- [Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premises](https://mlsanity.com/paper/2511.04020/) (2025)
- [Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning](https://mlsanity.com/paper/2602.01745/) (2026)
- [From Text to Multimodality: Exploring the Evolution and Impact of Large Language Models in Medical Practice](https://mlsanity.com/paper/2410.01812/) (2024)
- [CenterMamba-SAM: Center-Prioritized Scanning and Temporal Prototypes for Brain Lesion Segmentation](https://mlsanity.com/paper/2511.01243/) (2025)
- [LLM-Driven Adaptive Source-Sink Identification and False Positive Mitigation for Static Analysis](https://mlsanity.com/paper/2511.04023/) (2025)
- [ShieldedCode: Learning Robust Representations for Virtual Machine Protected Code](https://mlsanity.com/paper/2601.20679/) (2026)
- [Multi-Scenario Highway Lane-Change Intention Prediction: A Physics-Informed AI Framework for Three-Class Classification](https://mlsanity.com/paper/2509.17354/) (2025)
- [Hybrid Fuzzing with LLM-Guided Input Mutation and Semantic Feedback](https://mlsanity.com/paper/2511.03995/) (2025)
- [From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models](https://mlsanity.com/paper/2411.05036/) (2024)
- [Exploring Efficiency Frontiers of Thinking Budget in Medical Reasoning: Scaling Laws between Computational Resources and Reasoning Quality](https://mlsanity.com/paper/2508.12140/) (2025)

## Abstract (arXiv)

Modern vision-language models (VLMs) for driving assistants typically treat vehicle dynamics as a black box, resulting in decisions that lack awareness of the vehicle's real-time electro-mechanical state. To bridge this gap, we introduce the Electro-Visual-Language Assistant (EVLA) -- a novel framework that combines multi-modal scene understanding with real-time perception of the electrified powertrain state (e.g., motor torque, battery SOC). Our approach features two key innovations: first, a Unified Co-State Encoder (UCSE) that fuses visual, textual, and vehicle-state inputs into a shared latent representation, augmented with an Energy-Efficiency Field to model spatial energy costs; and second, an Electro-aware Structured Reasoning Chain (ESRC), which replaces external chain-of-thought prompting with an internal, deterministic reasoning process grounded in physical constraints and optimization objectives. Trained end-to-end with a physics-guided joint loss, EVLA learns to generate context-aware and energy-optimal driving decisions. Extensive evaluations on a driving QA benchmark demonstrate that EVLA substantially outperforms strong fine-tuned VLM baselines, improving the final score by +0.0871 and accuracy by +5.6%. Ablation studies validate the necessity of each component, and efficiency analyses show that EVLA achieves 36% faster inference than multi-stage pipelines. This work underscores that integrating vehicle-state awareness and structured physical reasoning is crucial for developing next-generation, physically-grounded driving assistants.