{"total":63,"rows":[{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2502.10391","title":"MM-RLHF: The Next Step Forward in Multimodal LLM Alignment","created":"2025-02-14","cited_by_count":83,"area":"mllm"},{"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":"2506.16402","title":"IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks","created":"2025-06-19","cited_by_count":41,"area":"agents"},{"id":"2502.12520","title":"SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning","created":"2025-02-18","cited_by_count":32,"area":"mllm"},{"id":"2505.11842","title":"Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs","created":"2025-05-17","cited_by_count":28,"area":"mllm"},{"id":"2507.02844","title":"Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection","created":"2025-07-03","cited_by_count":25,"area":"mllm"},{"id":"2507.18631","title":"Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment","created":"2025-07-24","cited_by_count":24,"area":"alignment"},{"id":"2501.18533","title":"Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models","created":"2025-01-30","cited_by_count":21,"area":"lr"},{"id":"2502.09990","title":"X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability","created":"2025-02-14","cited_by_count":20,"area":"alignment"},{"id":"2505.06538","title":"Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model","created":"2025-05-10","cited_by_count":19,"area":"lr"},{"id":"2512.04864","title":"Are Your Agents Upward Deceivers?","created":"2025-12-04","cited_by_count":16,"area":"agents"},{"id":"2509.21651","title":"Can AI Perceive Physical Danger and Intervene?","created":"2025-09-25","cited_by_count":14,"area":null},{"id":"2511.10222","title":"Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard","created":"2025-11-13","cited_by_count":13,"area":"safety"},{"id":"2502.11455","title":"Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training","created":"2025-02-17","cited_by_count":12,"area":"alignment"},{"id":"2502.12562","title":"SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings","created":"2025-02-18","cited_by_count":11,"area":"mllm"},{"id":"2508.05087","title":"JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering","created":"2025-08-07","cited_by_count":11,"area":"mllm"},{"id":"2504.12661","title":"VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization","created":"2025-04-17","cited_by_count":10,"area":"lr"},{"id":"2505.23793","title":"USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models","created":"2025-05-26","cited_by_count":10,"area":"mllm"},{"id":"2506.04704","title":"HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model","created":"2025-06-05","cited_by_count":9,"area":"mllm"},{"id":"2510.15253","title":"Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding","created":"2025-10-17","cited_by_count":9,"area":"rag"},{"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":"2505.14035","title":"ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs","created":"2025-05-20","cited_by_count":7,"area":"lr"},{"id":"2607.07907","title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","created":"2026-07-08","cited_by_count":7,"area":"safety"},{"id":"2505.16446","title":"Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models","created":"2025-05-22","cited_by_count":6,"area":"lr"},{"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":"2603.19092","title":"SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues","created":"2026-03-19","cited_by_count":4,"area":"mllm"},{"id":"2601.04043","title":"When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life","created":"2026-01-07","cited_by_count":3,"area":"mllm"},{"id":"2603.08486","title":"Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images","created":"2026-03-09","cited_by_count":3,"area":"mllm"},{"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":"2505.14340","title":"Plane Geometry Problem Solving with Multi-modal Reasoning: A Survey","created":"2025-05-20","cited_by_count":2,"area":"lr"},{"id":"2509.04403","title":"Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios","created":"2025-09-04","cited_by_count":2,"area":"mllm"},{"id":"2512.04895","title":"Chameleon: Adaptive Adversarial Agents for Scaling-Based Visual Prompt Injection in Multimodal AI Systems","created":"2025-12-04","cited_by_count":2,"area":"mllm"},{"id":"2602.03263","title":"CSR-Bench: A Benchmark for Evaluating the Cross-modal Safety and Reliability of MLLMs","created":"2026-02-03","cited_by_count":2,"area":"mllm"},{"id":"2602.03328","title":"GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and Audio","created":"2026-02-03","cited_by_count":2,"area":"safety"},{"id":"2607.09492","title":"Multimodal Reward Hacking in Reinforcement Learning","created":"2026-07-10","cited_by_count":2,"area":"mllm"},{"id":"2601.19507","title":"Automated Safety Benchmarking: A Multi-agent Pipeline for LVLMs","created":"2026-01-27","cited_by_count":1,"area":"mllm"},{"id":"2604.16358","title":"SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics","created":"2026-03-18","cited_by_count":1,"area":"alignment"},{"id":"2606.03089","title":"Constitutional On-Policy Safe Distillation","created":"2026-06-02","cited_by_count":1,"area":"distill"},{"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":"2608.23313","title":"EviSafe: Evidence-Grounded Safety Evaluation for Vision-Language Models","created":"2026-08-24","cited_by_count":1,"area":"mllm"},{"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":"2510.18619","title":"Visual Attention Reasoning via Hierarchical Search and Self-Verification","created":"2025-10-21","cited_by_count":0,"area":"lr"},{"id":"2601.04736","title":"Towards Multi-modal Multi-turn Safety: From Agentic Interaction to Strategic Alignment","created":"2026-01-08","cited_by_count":0,"area":"mllm"},{"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":"2603.09706","title":"OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences","created":"2026-03-10","cited_by_count":0,"area":"mllm"},{"id":"2606.02111","title":"Jailbreaking Multimodal Large Language Models using Multi-Clip Video","created":"2026-06-01","cited_by_count":0,"area":"mllm"},{"id":"2606.13709","title":"LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models","created":"2026-06-10","cited_by_count":0,"area":"moe"},{"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":"2607.21151","title":"V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure","created":"2026-07-23","cited_by_count":0,"area":"alignment"},{"id":"2608.09928","title":"Multimodal Model Diffing for Feature Discovery and Control","created":"2026-08-10","cited_by_count":0,"area":"mllm"},{"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},{"id":"2609.00206","title":"Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.02082","title":"Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.05525","title":"DIVA: Exploiting Cross-Step Conditional Propagation for Visual Jailbreaks in Discrete Diffusion Vision-Language Models","created":"2026-09-01","cited_by_count":0,"area":"mllm"},{"id":"2609.20850","title":"MME-Safety: A Fine-grained Benchmark for Safety Evaluation of MLLMs","created":"2026-08-08","cited_by_count":0,"area":"mllm"},{"id":"2609.38971","title":"Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners","created":"2026-09-30","cited_by_count":0,"area":"mllm"},{"id":"2609.39688","title":"ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.03938","title":"MLLMs Fail to Refuse when Using Tools Agentically","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.14094","title":"Scenes as an Attack Surface: Uncovering Scene-Grounded Safety Failures in MLLMs","created":"2026-10-08","cited_by_count":0,"area":"mllm"}],"next_cursor":null}