3 papers
cs.CV2026
nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving
Zhiyu Huang, Johnson Liu, Rui Song +13
Reasoning is essential for autonomous driving (AD) in long-tail scenarios, where vehicles must apply commonsense knowledge, understand spatial relations, infer agent interactions,…
cs.CV2026
SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model
Zewei Zhou, Ruining Yang, Xuewei +8
Vision-Language-Action (VLA) models offer a promising autonomous driving paradigm for leveraging world knowledge and reasoning capabilities, especially in long-tail scenarios. Howe…
cs.LG2024
Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras
Jun Yu, Yutong Dai, Xiaokang Liu +14
MTL is a learning paradigm that effectively leverages both task-specific and shared information to address multiple related tasks simultaneously. In contrast to STL, MTL offers a s…