NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
979 results for “keyword:"safety"” in ICLR 2027. 231 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Do Agents Do What Users Ask? Measuring Intent-State Consistency in Tool-Using Language Agents▼5.8k2.33
[PDF]Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults▼5.8k2.33
[PDF]Beyond Refuse-or-Comply: Fine-Grained Policy-to-Action Grounding in Safety-Aligned Language Models▼5.8k2.33
[PDF]When Speed Costs Accuracy: Causal Faithfulness of Component Attribution for Gender-Bias Localization▼1361.33
[PDF]LIBERO-Risk: Safety-Critical Scenario Generation and Process-Level Evaluation for Vision-Language-Action Models▲3.0k2.33
[PDF]Hijacking the Instruction Hierarchy in LLM Agents: From Semantic Injection to Persistent Compromise▼1.2k3.00
[PDF]Counterfactual Stress Testing of Behavioral Invariants in LLM Agents: A Study of Dynamic Authorization▼5.8k2.33
[PDF]To Cache or Not to Cache: Understanding and Mitigating Safety Incompatibility in Cross-Model KV Cache Reuse▲3.0k2.33
[PDF]Saturated Screening, Concentrated Cost: What a Full-Stack Ablation Table Reads in a Redundant Refusal Stack▼1.2k1.67
[PDF]Predictive Composite Guiding Vector Field for 3D Manipulator Path Following with Full-Link Obstacle Avoidance▼4.3k2.00
[PDF]BoundaryPlay: Improving Online Safety Self-Play via Counterfactual Request Construction▼4.3k2.00
[PDF]When to Wait, When to Intervene: Separating Hazard-Related Delays from Computational Congestion▼1.2k1.67
[PDF]MedicalPressureBench: Evaluating Care Pathway Integrity of Medical Agents Under Workplace Pressure▼4.3k2.00
[PDF]Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models▼5.8k2.33
[PDF]"Benign-Shifted Compliance": A Mechanistic Insight into Safety Behaviors of Diffusion Language Models under Adversarial Prefixes▲5.4k3.00
[PDF]Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models▲1.9k3.67
Withdrawn or desk rejected (231)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67
[PDF]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00