Representation Learning

On Causal Representation Learning with Internal Auxiliaries UAI 2026 On the Asymptotics of Self-Supervised Pre-training: Two-Stage M-Estimation and Representation Symmetry COLT 2026 On the Emergence and Test-Time Use of Structural Information in Large Language Models ACL 2026 Physical Object Understanding with a Physically Controllable World Model CVPR 2026 Predictive Regularization Against Visual Representation Degradation in Multimodal Large Language Models CVPR 2026 Provable Subspace Identification of Nonlinear Multi-view CCA UAI 2026 QiMeng-CRUX: Narrowing the Gap Between Natural Language and Verilog via Core Refined Understanding eXpression AAAI 2026 Reading Your Actions: Learning Generalizable Action Representations via Pre-training AEMG CVPR 2026 Reevaluating the Intra-Modal Misalignment Hypothesis in CLIP CVPR 2026 Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs ACL 2026 Representing Lean Proofs as Trajectories in Latent Space ACL 2026 REZE: Representation Regularization for Domain-adaptive Text Embedding Pre-finetuning ACL 2026 SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering ACL 2026 SARMAE: Masked Autoencoder for SAR Representation Learning CVPR 2026 Scalable Infinitesimal Generator–Based Koopman Learning for Long-Horizon Prediction L4DC 2026 Selective Amnesia using Contrastive Subnet Erasure for Class Level Unlearning in Vision Models CVPR 2026 SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning SemEval 2026 Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wild CVPR 2026 SIR: Structured Image Representations for Explainable Robot Learning CVPR 2026 SoloSemantics at SemEval-2026 Task 4: Triplet-Tuned MPNet for Story Similarity SemEval 2026 Spinfo Cologne at SemEval-2026 Task 4: Explainable Creation of Narrativity Embeddings SemEval 2026 TALAS: Teacher-Anchored Layer Alignment with Adaptive Sharpness-Aware Minimization for Embedding Distillation ACL 2026 Text-guided Feature Disentanglement for Cross-modal Gait Recognition CVPR 2026 The Universal Normal Embedding CVPR 2026 Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement ACL 2026