conftrace_

Xiaoya Lu

4 papers · 2025–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

AAAI (1) ACL (1) CVPR (1) EMNLP (1)

Top co-authors

Jing Shao (4) Dongrui Liu (3) Zeren Chen (2) Yijin Zhou (2) Lu Sheng (2) Zhanxu Xie (1) Lizhuang Ma (1) Zhijie Zheng (1) Lehan He (1) Xuhao Hu (1)

Research topics

Artificial Intelligence (4) Core AI (4) Machine Learning (1) Natural Language Processing (1) Learning Types (1) Resources & Methods (1)

Keywords

vision-language model (2) benchmark evaluation (1) embodied ai (1) feature representation (1) distribution shift (1) adversarial attack (1) safety benchmark (1) spatial reasoning (1) semantic reasoning (1) jailbreak defense (1) geometric constraint (1) llm safety (1) safety training (1) risk mitigation (1) safety vulnerability (1) safety boundary (1) large language model (1) boundary-safe representation (1) interactive safety (1) representation learning (1)

Papers

Geometrically-Constrained Agent for Spatial Reasoning CVPR 2026 IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks AAAI 2026 LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts ACL 2025 X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Jailbreak Attacks without Compromising Usability EMNLP 2025