Showing 281–300 of 2,256 results
/ Date/ Name
Apr 20, 2026Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use AgentsApr 20, 2026OmniMouse: Scaling properties of multi-modal, multi-task Brain Models on 150B Neural TokensApr 20, 2026ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward SystemApr 20, 2026Towards Understanding the Robustness of Sparse AutoencodersApr 20, 2026Towards Optimal Agentic Architectures for Offensive Security TasksApr 20, 2026Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model TrainingApr 20, 2026Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM JailbreaksApr 20, 2026Tight Auditing of Differential Privacy in MST and AIMApr 20, 2026Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMsApr 20, 2026Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented GenerationApr 20, 2026AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation QuantizationApr 20, 2026Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student AttacksApr 20, 2026ExAI5G: A Logic-Based Explainable AI Framework for Intrusion Detection in 5G NetworksApr 20, 2026Owner-Harm: A Missing Threat Model for AI Agent SafetyApr 20, 2026RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary ProgramsApr 20, 2026Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLMApr 20, 2026From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic ComputersApr 20, 2026Understanding Secret Leakage Risks in Code LLMs: A Tokenization PerspectiveApr 20, 2026Party Autonomy in Determining the Law Applicable to Non-contractual Obligations concerning Cross-Border Data TransfersApr 20, 2026Position: No Retroactive Cure for Infringement during Training