Representation Learning

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story EACL 2026 USE: A Unified Model for Universal Sound Separation and Extraction AAAI 2026 VAEVQ: Enhancing Discrete Visual Tokenization Through Variational Modeling AAAI 2026 Valid Inference for Treatment Effects under Multimodal Confounding CLeaR 2026 VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation AAAI 2026 Vibe Spaces for Creatively Connecting and Expressing Visual Concepts CVPR 2026 Vietnamese Automatic Speech Recognition: A Revisit EACL 2026 ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance WACV 2026 VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval EACL 2026 Visual Bridge: Universal Visual Perception Representations Generating AAAI 2026 ViType: High-Fidelity Visual Text Rendering via Glyph-Aware Multimodal Diffusion AAAI 2026 VLHSA: Vision-Language Hierarchical Semantic Alignment for Jigsaw Puzzle Solving with Eroded Gaps (Student Abstract) AAAI 2026 Wavelet Enhanced Adaptive Frequency Filter for Sequential Recommendation AAAI 2026 WhisperDiari: A Whisper-Based Speaker Diarization Framework in Token Space Leveraging Semantic and Speaker Information for Better Text Adaptability AAAI 2026 Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations UAI 2026 Who You Are, What You Say: Intra- and Inter- Context Personality for Emotion Recognition in Conversation EACL 2026 Why Isn’t Relational Learning Taking Over the World? AAAI 2026 Wi-CBR: Salient-aware Adaptive WiFi Sensing for Cross-domain Behavior Recognition AAAI 2026 X-MoGen: Unified Motion Generation Across Humans and Animals AAAI 2026 Zero-Shot Coreset Selection via Iterative Subspace Sampling WACV 2026 X-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs ICLR 2025 3D Denoisers Are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation AAAI 2025 3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding ICCV 2025 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting ICLR 2025 3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling ICLR 2025