collaborators

11 papers

cs.AI2026

VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora

Yuting Xu, Jiayi Tian, Jian Liang +4

Existing benchmarks have laid the foundation for travel planning agents by establishing API-centric paradigms. However, as the capabilities of Autonomous Agents continue to advance…

cs.CV2026

TrackRef3D: Multi-View Consistent Track-then-Label for Open-World Referring Segmentation in 3D Gaussian Splatting

Yuyang Tan, Renhe Zhang, Hang Zhang +2

Referring 3D Gaussian Splatting (R3DGS), which utilizes natural language for 3D object segmentation, has emerged as a crucial capability for embodied AI. However, existing methods…

cs.CL2026

What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QA

Yuelyu Ji, Min Gu Kwak, Hang Zhang +3

Medical RAG needs evidence-grounded claims, so plugging a claim-level NLI checker into retrieval-augmented RL is intuitive. \textbf{We find that the checker's \emph{output distribu…

cs.CV2026

ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs

Jiangyang Li, Cong Wan, Changjie Wu +8

Reliable spatial reasoning remains a core bottleneck for vision-language models (VLMs). Existing mainstream training paradigms for spatial reasoning largely rely on outcome alignme…

cs.CV2026

3D-Layout-R1: Structured Reasoning for Language-Instructed Spatial Editing

Haoyu Zhen, Xiaolong Li, Yilin Zhao +5

Large Language Models (LLMs) and Vision Language Models (VLMs) have shown impressive reasoning abilities, yet they struggle with spatial understanding and layout consistency when p…

cs.HC2026

Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI

Sicheng Yang, Yukai Huang, Weitong Cai +8

What if accessing the web did not require a screen, a stable desk, or even free hands? For people navigating crowded cities, living with low vision, or experiencing cognitive overl…