arXiv Computer Vision
KDTwin: Task-Aware Knowledge Distillation for Lightweight Multi-Task Driving Scene Segmentation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jun 6
Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous Driving
arXiv:2601. 21288v2 Announce Type: replace Abstract: Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain.
arXiv Computer Vision
Oct 1
AHMAD: Adaptive Hybrid Multi-task Vision Learning with Assisted Distillation for Keypoint Detection
arXiv:2609.35490v2 Announce Type: replace Abstract: Generalist multitasking vision models aim to unify multiple vision tasks within a single framework, enabling more efficient and versatile learning....
arXiv Computer Vision
2d ago
DSRS: Teaching MLLMs to Perceive, Reason, and Segment in Complex Driving Scenes
arXiv:2611.06160v1 Announce Type: new Abstract: Existing reasoning segmentation frameworks typically employ multimodal large language models (MLLMs) with broad world knowledge to extract semantics in...
arXiv Machine Learning
Jun 15
RT-VLA: Real-Time Vision-Language-Action Models via Knowledge Distillation
arXiv:2606. 14010v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for end-to-end autonomous driving by jointly modeling visual perception, language reasoning, explainability and action prediction.
arXiv AI
Aug 10
WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA
arXiv:2608. 01035v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by high computational latency and exposure bias arising from sequential autoregressive decoding.
arXiv Computer Vision
Oct 9
HENet++: Hybrid Encoding and Multi-task Learning for 3D Perception and End-to-end Autonomous Driving
HENet++ is a unified framework that combines a hybrid image encoding strategy—using a large encoder for short‑term frames and a lightweight encoder for long‑term temporal context—to balance accuracy and efficiency in 3D perception for autonomous driving. It jointly extracts dense background and sparse foreground features, enabling task‑specific representations that reduce cumulative errors and enrich downstream prediction and planning modules. The approach supports diverse 3D feature extraction pipelines, multi‑modal inputs (camera and radar), and achieves state‑of‑the‑art results on nuScenes and NAVSIM benchmarks, including the lowest collision rate on nuScenes planning.