Xiaodong Cai — accepted AI-conference papers

2026

3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models

Shaoxiong Zhan, Yanlin Lai, Zheng Liu, Zijian Lin, Lin Hai, Xiaodong Cai +3

ICML 2026oral

Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks like block counting. This capability mismatch reveals a critical "spatial intelligence gap," where models fail to construct coherent 3D mental representations…

Cited by 0 Source ↗Scholar ↗

2026

AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition

Ruipeng Wang, Yuxin Chen, Yukai Wang, Chang Wu, Junfeng Fang, Xiaodong Cai +6

ICML 2026poster

As LLM-based agents are increasingly deployed in real-world workflows, existing agent benchmarks---often built on idealized, noise-free assumptions---fall short of characterizing agents' robustness under imperfect user instructions and unreliable tool feedback. To address this gap, we introduce **Ag…

Cited by 0 Source ↗Scholar ↗