Junhong Lin

most citedLarge Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review

75 citations · 79 across the 4 of their papers we have counts for

collaborators

Showing cs.ROShow all

2 papers · 1 filter

cs.RO2026

Sometimes You Gotta Run Before You Can Walk: Run-then-Walk Scheduling Strategy for VLM Autonomous Driving

Yuqi Ye, Shangkun Sun, Junhong Lin +6

Recent VLM-based autonomous driving planners adopt GRPO-style reinforcement learning to optimize driving performance. However, existing GRPO recipes either optimize driving efficie…

cs.RO2026

$A u t oD r i v e - P^{3}$ : Unified Chain of Perception-Prediction-Planning Thought via Reinforcement Fine-Tuning

Yuqi Ye, Zijian Zhang, Junhong Lin +3

Vision-language models (VLMs) are increasingly being adopted for end-to-end autonomous driving systems due to their exceptional performance in handling long-tail scenarios. However…

Sometimes You Gotta Run Before You Can Walk: Run-then-Walk Scheduling Strategy for VLM Autonomous Driving

AutoDrive-P3: Unified Chain of Perception-Prediction-Planning Thought via Reinforcement Fine-Tuning

$A u t oD r i v e - P^{3}$ : Unified Chain of Perception-Prediction-Planning Thought via Reinforcement Fine-Tuning