Artificial Intelligence

Beyond Pixel Uncertainty: Bounding the OoD Objects in Road Scenes ICCV 2025 Beyond Pointwise Scores: Decomposed Criteria-Based Evaluation of LLM Responses EMNLP 2025 Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs ACL 2025 Beyond Prompt Engineering: A Reinforced Token-Level Input Refinement for Large Language Models AAAI 2025 Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms ACL 2025 Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation ACL 2025 Beyond Reconstruction: Generating Privacy-Preserving Clinical Letters NAACL 2025 Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation EMNLP 2025 Beyond Self-Reports: Multi-Observer Agents for Personality Assessment in Large Language Models EMNLP 2025 Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity ACL 2025 Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions ICML 2025 Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge CVPR 2025 Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection ACL 2025 Beyond Simple Edits: Composed Video Retrieval with Dense Modifications ICCV 2025 Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution ICLR 2025 Beyond Single-Feature Importance with ICECREAM CLeaR 2025 Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip? EMNLP 2025 Beyond Single-Modal Boundary: Cross-Modal Anomaly Detection through Visual Prototype and Harmonization CVPR 2025 Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosis ACL 2025 Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing EMNLP 2025 Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems EMNLP 2025 Beyond Statistical Analysis: Multimodal Framework for Time Series Forecasting with LLM-Driven Temporal Pattern IJCAI 2025 Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction EMNLP 2025 Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs ACL 2025 Beyond Surface Simplicity: Revealing Hidden Reasoning Attributes for Precise Commonsense Diagnosis ACL 2025