Representation Learning

Hier-COS: Making Deep Features Hierarchy-aware via Composition of Orthogonal Subspaces CVPR 2026 Human Geometry Distribution for 3D Animation Generation CVPR 2026 Hyperbolic Busemann Neural Networks CVPR 2026 HypeVPR: Exploring Hyperbolic Space for Perspective to Equirectangular Visual Place Recognition CVPR 2026 Identifying Weight-Variant Latent Causal Models JMLR 2026 Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment UAI 2026 Intervening to learn and compose causally disentangled representations CLeaR 2026 Intrinsic Concept Extraction Based on Compositional Interpretability CVPR 2026 Is the Modality Gap a Bug or a Feature? A Robustness Perspective CVPR 2026 Lacuna Inc. at SemEval-2026 Task 4: Structurally Gated State-Space Models for Disentangling Narrative Similarity SemEval 2026 Language Models Struggle to Use Representations Learned In-Context ACL 2026 LA-Pose: Latent Action Pretraining Meets Pose Estimation CVPR 2026 LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations ACL 2026 Learning Convex Decomposition via Feature Fields CVPR 2026 LLM Beliefs Are in Their Heads ACL 2026 LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals ACL 2026 Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos CVPR 2026 LoST: Level of Semantics Tokenization for 3D Shapes CVPR 2026 Markovian Linguistic-Temporal Bridge: Unlocking the Potential of LLMs for Time Series Forecasting ACL 2026 Mendel292 at SemEval-2026 Task 4: Disentangled Narrative Embeddings for Story Similarity SemEval 2026 Mitigating Spurious Correlations in Text Classification Using Latent Space Geometry ACL 2026 Modeling the Visual Ambiguity of Human Sketches CVPR 2026 MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation ACL 2026 Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective ACL 2026 Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies JMLR 2026