Representation Learning

AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling ACL 2026 AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM ACL 2026 A framework for analyzing concept representations in neural models CoNLL 2026 Anchoring the Affective Manifold: Learning Canonical and Disentangled Representations via Generative Cross-Modal Alignment ACL 2026 Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token ACL 2026 Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding ACL 2026 Conflict-Aware Adaptive Cross-Reconstruction for Multimodal Sentiment Analysis CVPR 2026 Coordinate Denoising for Non-Equilibrium Molecular Representation Learning CVPR 2026 Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation CVPR 2026 Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining ACL 2026 Cross-Modal Taxonomic Generalization in (Vision-) Language Models ACL 2026 CUNI at SemEval-2026 Task 4: Multi-Head Narrative Aspect Disentanglement via Entangled Synthetic Dataset SemEval 2026 Deep Feature Deformation Weights CVPR 2026 Diffusion Mental Averages CVPR 2026 Diffusion-Pretrained Dense and Contextual Embeddings ACL 2026 Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention CLeaR 2026 DUTIR at SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning SemEval 2026 DVI-DTM: Dual-View Representation Learning for Interpretable Short Text Dynamic Topic Modeling ACL 2026 Efficient and High-Fidelity Omni Modality Retrieval CVPR 2026 Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI ACL 2026 FlowComposer: Composable Flows for Compositional Zero-Shot Learning CVPR 2026 From Graphs to Hypergraphs: Enhancing Aspect-Term Sentiment Analysis via Multi-Level Relational Modeling ACL 2026 From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts? ACL 2026 From Moves to Paths: A Hierarchical Framework for Trajectory Representation Learning UAI 2026 GASE: Graph-Aware Semantic Embedding Learning with Frozen LLMs for Text-Attributed Graphs ACL 2026