Representation Learning

TrajTok: Learning Trajectory Tokens Enhances Video Understanding CVPR 2026 ttda704 at SemEval-2026 Task 4: Modeling Narrative Structures via Pseudonymization and Multi-View Sentence Alignment SemEval 2026 Tunable Soft Equivariance with Guarantees CVPR 2026 UM–ProtoShare: UNet-Guided, Multi-scale Shared Prototypes for Interpretable Brain Tumour Classification Using Multi-sequence 3D MRI MIDL 2026 Unified Latent Space for Understanding and Generation via Semantic Auto-encoder CVPR 2026 UniLight: A Unified Representation for Lighting CVPR 2026 Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods CVPR 2026 UNUM: A New Framework for Network Control NSDI 2026 VRCLIP: Multimodal Canonical Correlation Alignment for CLIP-Driven Vision-Radio Person Re-Identification CVPR 2026 Weight Space Representation Learning via Neural Field Adaptation CVPR 2026 Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations UAI 2026 Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings ACL 2026 Analyzing Generative Models by Manifold Entropic Metrics AISTATS 2025 An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Interspeech 2025 Contextual Document Embeddings ICLR 2025 Deep Signature: Characterization of Large-Scale Molecular Dynamics ICLR 2025 DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech Interspeech 2025 DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors ICLR 2025 Dog2vec: Self-Supervised Pre-Training for Canine Vocal Representation Interspeech 2025 Effective post-training embedding compression via temperature control in contrastive training ICLR 2025 Enhancing Audio Deepfake Detection by Improving Representation Similarity of Bonafide Speech Interspeech 2025 FreeCodec: A Disentangled Neural Speech Codec with Fewer Tokens Interspeech 2025 Holographic Node Representations: Pre-training Task-Agnostic Node Embeddings ICLR 2025 Hyperboloid GPLVM for Discovering Continuous Hierarchies via Nonparametric Estimation AISTATS 2025 Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class Hierarchy AISTATS 2025