Representation Learning

Universality of Real Minimal Complexity Reservoir AAAI 2025 Universal Length Generalization with Turing Programs ICML 2025 Universal Scene Graph Generation CVPR 2025 Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment ICML 2025 UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction ICCV 2025 Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient AAAI 2025 Unlocking Better Closed-Set Alignment Based on Neural Collapse for Open-Set Recognition AAAI 2025 Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning ICLR 2025 Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering ACL 2025 Unlocking Global Optimality in Bilevel Optimization: A Pilot Study ICLR 2025 Unlocking the Power of LSTM for Long Term Time Series Forecasting AAAI 2025 Unnatural Languages Are Not Bugs but Features for LLMs ICML 2025 Unpacking Let Alone: Human-Scale Models Generalize to a Rare Construction in Form but not Meaning EMNLP 2025 Unsupervised Concept Vector Extraction for Bias Control in LLMs EMNLP 2025 Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution AAAI 2025 Unsupervised Disentanglement of Content and Style via Variance-Invariance Constraints ICLR 2025 Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teaming IJCAI 2025 Unsupervised Identification of Protein Compositions and Conformations via Implicit Content-Transformation Disentanglement ICCV 2025 Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstruction AAAI 2025 Unveiling Language Competence Neurons: A Psycholinguistic Approach to Model Interpretability COLING 2025 Unveiling Multi-View Anomaly Detection: Intra-view Decoupling and Inter-view Fusion AAAI 2025 UoL-UPF at TSAR 2025 Shared Task A Generate-and-Select Approach for Readability-Controlled Text Simplification EMNLP 2025 Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging ACL 2025 Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation EMNLP 2025 UPSC2M: Benchmarking Adaptive Learning from Two Million MCQ Attempts ACL 2025