2 papers
cs.CV2026
Dynamic Alignment Compensation for Hallucination Mitigation in Large Vision-Language Models
Kairong Yu, Zixin Zhu, Le Yu +1
Large Vision-Language Models (LVLMs) remain prone to hallucinations, producing responses that are irrelevant or inconsistent with the multimodal input. Existing mitigation methods…
cs.AI2026
EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints
Ao Zhou, Bo Dai, Le Yu +5
Vision-Language-Action (VLA) models have emerged as a promising foundation for Embodied AI, but their high inference cost poses significant challenges for deployment in robotic sys…