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979 results for “keyword:"safety"” in ICLR 2027. 231 withdrawn or desk rejected listed apart.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]Rethinking Safety Reward Models in Long-Context Settings: Systematic Evaluation and Reliable Contextual Modeling▲9.2k2.67
[PDF]Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs▼4.3k2.00
[PDF]Disentangling Safety and Capability in Large Language Models via Causal Interventional Decomposition▼1361.33
[PDF]Linear Separability Is Not Input Controllability: Intermediate-Layer Jailbreak on VLMs▲6.1k2.00
[PDF]SAFETYEDIT: Sparse Internal Targets with Prompt-Wide Control for LLM Jailbreak Backdoors▼4.5k2.67
[PDF]Guarding a Needle in the Haystack: A Real-Time Policy-Following Streaming Video Guardrail▲3952.67
[PDF]Benign Safety Is Not a Robustness Certificate: Evidence of a Structural Evaluation Gap Across Attack Conditions▲11.00
[PDF]Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models▲3.0k2.33
[PDF]Balanced Perturbation and Subspace Erasure Do Not Identify What an Activation Monitor Reads▼1.2k1.67
[PDF]Pressure Is Not Enough: A Causal Test of Whether Optimization Induces Encoded Chain-of-Thought▼1.2k1.67
[PDF]Adaptation or Poisoning? Security Risks of Conversational Test-Time Learning in Large Language Models▲3.0k2.33
[PDF]When Recovery Creates Resistance: Instrumental Shutdown Avoidance from Gridworlds to Language-Model Agents▼5.3k1.33
[PDF]CONFORMALGUARD: DISTRIBUTION-FREE FALSEBLOCK GUARANTEES FOR MULTI-AGENT LLM SYSTEMS VIA CONFORMAL PREDICTION ON DYNAMIC EXECUTION GRAPHS▼3.7k2.25
[PDF]Disagreement in, Disagreement Out? Uneven Downstream Effects of Harm Classifier Differences▼5.8k2.33
[PDF]Towards a Theoretical Foundation for Tool-Augmented LLM Skill Libraries: The Price of Composition, Propagation, and Safety Under Evolution▼4.3k2.00
Withdrawn or desk rejected (231)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