collaborators

5 papers

cs.CV2026

HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task

Xiaoya Lu, Yijin Zhou, Zeren Chen +6

Vision-Language Models (VLMs) empower embodied agents to execute complex instructions, yet they remain vulnerable to contextual safety risks where benign commands become hazardous…

cs.AI2025

IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks

Xiaoya Lu, Zeren Chen, Xuhao Hu +5

Flawed planning from VLM-driven embodied agents poses significant safety hazards, hindering their deployment in real-world household tasks. However, existing static, non-interactiv…

cs.AI2025

Geometrically-Constrained Agent for Spatial Reasoning

Zeren Chen, Xiaoya Lu, Zhijie Zheng +6

Vision Language Models (VLMs) exhibit a fundamental semantic-to-geometric gap in spatial reasoning: they excel at qualitative semantic inference but their reasoning operates within…

cs.CL2025

Systematic Reward Gap Optimization for Mitigating VLM Hallucinations

Lehan He, Zeren Chen, Zhelun Shi +3

The success of Direct Preference Optimization (DPO) in mitigating hallucinations in Vision Language Models (VLMs) critically hinges on the true reward gaps within preference pairs.…

cs.CL2025

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation

Lijun Li, Zhelun Shi, Xuhao Hu +5

Text-to-image (T2I) models have rapidly advanced, enabling the generation of high-quality images from text prompts across various domains. However, these models present notable saf…