{"total":13,"rows":[{"id":"2412.04455","title":"Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection","created":"2024-12-05","cited_by_count":63,"area":null},{"id":"2509.21651","title":"Can AI Perceive Physical Danger and Intervene?","created":"2025-09-25","cited_by_count":14,"area":null},{"id":"2510.08211","title":"LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions","created":"2025-10-09","cited_by_count":8,"area":null},{"id":"2510.18214","title":"VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2502.16770","title":"LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2505.04673","title":"REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLM","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2502.05242","title":"Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2606.09068","title":"Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2504.04997","title":"SurvSurf: a partially monotonic neural network for first-hitting time prediction of intermittently observed discrete and continuous sequential events","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2602.03268","title":"Unveiling Covert Toxicity in Multimodal Data via Toxicity Association Graphs: A Graph-Based Metric and Interpretable Detection Framework","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2603.03324","title":"Controlling Chat Style in Language Models via Single-Direction Editing","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2607.00576","title":"Safe Alone, Unsafe Together: Safeguarding Against Implicit Toxicity When Benign Images Combine","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.29098","title":"SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard Models","created":"2026-08-29","cited_by_count":0,"area":null}],"next_cursor":null}