Artificial Intelligence

From Lists to Emojis: How Format Bias Affects Model Alignment ACL 2025 From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection ICML 2025 From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement EMNLP 2025 From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding EMNLP 2025 From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications ICML 2025 From Measurement to Mitigation: Exploring the Transferability of Debiasing Approaches to Gender Bias in Maltese Language Models ACL 2025 From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language Models ICML 2025 From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs ACL 2025 From Monolingual to Bilingual: Investigating Language Conditioning in Large Language Models for Psycholinguistic Tasks IJCNLP 2025 From Movement Memories to Robotic Dialogue: A Language-Mediated Pipeline for Somatic Machine Translation NeurIPS 2025 From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons CVPR 2025 From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment ACL 2025 From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modeling EMNLP 2025 From Noise to Nuance: Enriching Subjective Data Annotation through Qualitative Analysis EMNLP 2025 From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation ACL 2025 From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning ICCV 2025 From Observation to Understanding: Front-Door Adjustments with Uncertainty Calibration for Enhancing Egocentric Reasoning in LVLMs ACL 2025 From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment ACL 2025 From Panels to Prose: Generating Literary Narratives from Comics ICCV 2025 From Parameters to Performance: A Data-Driven Study on LLM Structure and Development EMNLP 2025 From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information? ICML 2025 From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers AAAI 2025 From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs ACL 2025 From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model EMNLP 2025 From Perception to Reasoning: Enhancing Vision-Language Models for Mobile UI Understanding ACL 2025