Machine Learning

From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras ICCV 2025 From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization NAACL 2025 From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency ICLR 2025 From Sparse to Complete: Semantic Understanding Based on Stroke Evolution in On-the-fly Sketch-based Image Retrieval IJCAI 2025 From Sparse to Dense Functional Data in High Dimensions: Revisiting Phase Transitions from a Non-Asymptotic Perspective JMLR 2025 From Stories to Statistics: Methodological Biases in LLM-Based Narrative Flow Quantification CoNLL 2025 From Syntax to Semantics: Evaluating the Impact of Linguistic Structures on LLM-Based Information Extraction ACL 2025 From Teacher to Student: Tracking Memorization Through Model Distillation ACL 2025 From Templates to Natural Language: Generalization Challenges in Instruction-Tuned LLMs for Spatial Reasoning IJCNLP 2025 From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition EMNLP 2025 From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs NAACL 2025 From Text to Multi-Modal: Advancing Low-Resource-Language Translation through Synthetic Data Generation and Cross-Modal Alignments NAACL 2025 From Theory to Practice: Rethinking Green and Martin Kernels for Unleashing Graph Transformers ICML 2025 From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs ICML 2025 From Tokens to Lattices: Emergent Lattice Structures in Language Models ICLR 2025 From Tokens to Words: On the Inner Lexicon of LLMs ICLR 2025 From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval EMNLP 2025 From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining ICML 2025 From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE Control ICML 2025 From Understanding to Generation: An Efficient Shortcut for Evaluating Language Models EMNLP 2025 From Visual Explanations to Counterfactual Explanations with Latent Diffusion WACV 2025 From Weak Labels to Strong Results: Utilizing 5,000 Hours of Noisy Classroom Transcripts with Minimal Accurate Data Interspeech 2025 From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control ICML 2025 From Words to Worth: Newborn Article Impact Prediction with LLM AAAI 2025 From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Test EMNLP 2025