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979 results for “keyword:"safety"” in ICLR 2027. 231 withdrawn or desk rejected listed apart.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]When and Why Do Agents Become Unsafe? A Trajectory-Aware Benchmark for Multi-Turn Agent Safety Evaluation▲3952.67
[PDF]WARD: Watching Actions via Latent-Space Reachability for Runtime Backdoor Defense in VLA Models▼1.2k3.00
[PDF]SCOPE: Sparse Coordinate Suppression Complements Activation Steering in Vision-Language Models▼5.8k2.33
[PDF]Making Your LLMs More Objective: Stabilizing LLM Safety Behavior Across Traits with Trait-Invariant Safety Tuning▼5.9k2.50
[PDF]Seeing More, Refusing Less: Two Mechanisms of Safety Erosion in Video Large Language Models▲3.0k2.33
[PDF]From Approval to Abuse: Privilege Escalation Attacks on Harness-Protected Coding Agents▼1361.33
[PDF]Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections▼4.3k2.00
[PDF]Rubric-to-Segment: Criterion-grounded Semantic Credit Assignment for Language Model Alignment▲5103.00
Withdrawn or desk rejected (231)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