Scene-Adaptive Readout and Decoding in Diffusion Driving VLAs
cs.CV, cs.AI, cs.RO
Submitted: 2026-11-01
Updated: 2026-11-09
Code: https://github.com/sjyu001/SARD
Terminology
Sources
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Self Speculative Decoding for Diffusion Large Language Models
- MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving
- IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model
- Diffusion Language Models Know the Answer Before Decoding
- FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving
- LightEMMA: A Longitudinal Evaluation of Vision-Language Models for Autonomous Driving
- Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
- Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
- DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
- Unifying Language-Action Understanding and Generation for Autonomous Driving
- Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving
- ST-MoE: Designing Stable and Transferable Sparse Expert Models
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