Artificial Intelligence

When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training EACL 2026 When Models Hesitate: Answer Instability as a Label-Free Uncertainty Signal for LLMs ACL 2026 When More Words Say Less: Decoupling Length and Specificity in Image Description Evaluation ACL 2026 When Natural Strategies Meet Fuzziness and Resource-Bounded Actions AAAI 2026 When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models CVPR 2026 When One LLM Drools, Multi-LLM Collaboration Rules ACL 2026 When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents ACL 2026 When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection ACL 2026 When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing AAAI 2026 When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models EACL 2026 When Proxy Agents Disagree, Do Humans Mirror? Manipulating Human Behavior in Moral Dilemmas Through Agents AAAI 2026 When Reasoning Collapses: A Depth-Aware Probe into LLM Reasoning (Student Abstract) AAAI 2026 When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models CVPR 2026 When Robots Should Say ''I Don't Know'': Benchmarking Abstention in Embodied Question Answering CVPR 2026 When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models AAAI 2026 When Seeing Is not Enough: Revealing the Limits of Active Reasoning in MLLMs ACL 2026 When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models ACL 2026 When Semantic Overlap Is Not Enough: Cross-Lingual Euphemism Transfer Between Turkish and English EACL 2026 When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ Toxicity AAAI 2026 When Speed Meets Intelligence: Scalable Conversational NER in an Ever-evolving World EACL 2026 When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables ACL 2026 When the Domain Expert Has No Time and the LLM Developer Has No Clinical Expertise: Real-World Lessons from LLM Co-Design in a Safety-Net Hospital AAAI 2026 When the Model Said ‘No Comment’, We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified EACL 2026 When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs CVPR 2026 When Top-ranked Recommendations Fail: Modeling Multi-Granular Negative Feedback for Explainable and Robust Video Recommendation AAAI 2026