3 papers
cs.AI2026
VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?
Yansong Ning, Jingwen Ye, Zhongkai Wu +5
Constructing an interactive 3D open world from a user query is important. However, existing methods are primarily evaluated on idealized, simple queries, making it difficult to sys…
cs.AI2026
HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs
Yansong Ning, Mianpeng Liu, Jingwen Ye +2
Hybrid-reasoning large language models (LLMs) expose explicit controls over reasoning effort, allowing users or systems to trade off answer quality against inference cost. However,…
cs.CV2025
Beyond ImageNet: Understanding Cross-Dataset Robustness of Lightweight Vision Models
Weidong Zhang, Pak Lun Kevin Ding, Huan Liu
Lightweight vision classification models such as MobileNet, ShuffleNet, and EfficientNet are increasingly deployed in mobile and embedded systems, yet their performance has been pr…