paper-with-me

Papers

BucketKD: A Safety-Aware Bucket-Based Knowledge Distillation Framework for End-to-End Motion Planning

2026-07-12 · Md Nahidul Islam, Mohd Hasan Ali, Dipankar Dasgupta, Myounggyu Won arxiv

End-to-end motion planning has emerged as a promising paradigm in autonomous driving, directly mapping raw sensor data to control commands via deep neural networks. Despite its advantages, its large model size hinders deployment in resource-constrained platforms. In this paper, we present BucketKD, a bucket-based knowledge distillation framework that yields compact and safety-aware end-to-end planners. Compared to the state-of-the-art approach, which relies on simplified planning state representations, BucketKD discretizes critical environmental variables into adaptive buckets that capture richer scene semantics while preserving efficiency. In addition, we design a safety-aware waypoint attention mechanism that evaluates each waypoint's risk level by accounting for both obstacle proximity and relative motion through a time-to-collision (TTC) formulation widely used in transportation research. This enables the student model to better retain safety-critical behaviors during distillation. Extensive experiments in CARLA using the Bench2Drive dataset show that BucketKD significantly outperforms the state-of-the-art in both planning accuracy and safety while maintaining strong compression ratios.

📄 PDF Abstract BibTeX arXiv:2607.10565

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationAutonomous DrivingMotion Planning

Similar Papers 제목 키워드 기반

Combating the Bucket Effect:Multi-Knowledge Alignment for Medication Recommendation

2025-04-25 · Xiang Li, Haixu Ma, Guanyong Wu, Shi Mu 외

Medication recommendation is crucial in healthcare, offering effective treatments based on patient's electronic health records (EHR). Previous studies show that integrating more medication-related knowledge improves medi…

Contrastive Learning

Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes

2026-06-25 · Jeremias Ferrao, Niclas Müller-Hof, Iustin Sîrbu, Traian Rebedea 외 arxiv

We argue that safety classifiers should model user intent as an explicit signal between the prompt and the final label. To study this, we introduce AIMS, a human-annotated dataset of 1,724 difficult safety prompts, each …

Reinforcement Learning

UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization, and Distillation

2026-02-09 · Jonathan von Rad, Yong Cao, Andreas Geiger arxiv

Model compression is increasingly essential for deploying large language models (LLMs), yet existing comparative studies largely focus on pruning and quantization evaluated primarily on knowledge-centric benchmarks. Thus…

Knowledge DistillationModel Compression

BucketServe: Bucket-Based Dynamic Batching for Smart and Efficient LLM Inference Serving

2025-07-23 · Wanyi Zheng, Minxian Xu, Shengye Song, Kejiang Ye arxiv

Large language models (LLMs) have become increasingly popular in various areas, traditional business gradually shifting from rule-based systems to LLM-based solutions. However, the inference of LLMs is resource-intensive…

PolyAlign: Conditional Human-Distribution Alignment

2026-06-11 · L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva, Xiao Wu 외 arxiv

Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective for improving average helpfulness, this ca…