Representation Learning

AstroLoc: Robust Space to Ground Image Localizer ICCV 2025 Asymmetric Cross-Modal Hashing Based on Formal Concept Analysis AAAI 2025 A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning AISTATS 2025 ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling ICCV 2025 Attention Speaks Volumes: Localizing and Mitigating Bias in Language Models ACL 2025 Attribute-formed Class-specific Concept Space: Endowing Language Bottleneck Model with Better Interpretability and Scalability CVPR 2025 A Unified Data Representation Learning for Non-parametric Two-sample Testing UAI 2025 A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning AISTATS 2025 A Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse Artifacts CVPR 2025 AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360deg Unbounded Scene Inpainting CVPR 2025 Automatic concept extraction for learning domain modeling: A weakly supervised approach using contextualized word embeddings ACL 2025 A Variational Information Theoretic Approach to Out-of-Distribution Detection ICML 2025 Avoidance Decoding for Diverse Multi-Branch Story Generation EMNLP 2025 Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation ACL 2025 Band-Split Self-supervised Mamba for Infant-centered Audio Analysis Interspeech 2025 Bayesian-Inspired Space-Time Superpixels ICCV 2025 BBN-U.Oregon’s ALERT system at GenAI Content Detection Task 3: Robust Authorship Style Representations for Cross-Domain Machine-Generated Text Detection COLING 2025 BCE vs. CE in Deep Feature Learning ICML 2025 Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey ACL 2025 Behaviour Preference Regression for Offline Reinforcement Learning AAAI 2025 Better Embeddings with Coupled Adam ACL 2025 Beyond Federated Prototype Learning: Learnable Semantic Anchors with Hyperspherical Contrast for Domain-Skewed Data AAAI 2025 Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance ICML 2025 Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation ACL 2025 Beyond Position: the emergence of wavelet-like properties in Transformers ACL 2025