Representation Learning

ART: Actor-Related Tubelet for Detecting Complex-shaped Action Tubes WACV 2026 A Subword Embedding Approach for Variation Detection in Luxembourgish User Comments EACL 2026 ATM: Enhanced Alignment for Text-to-Motion Generation WACV 2026 Atom-level Adaptive Receptive Fields: A Pruning-Based Encoder for 2D Molecular Graphs (Student Abstract) AAAI 2026 Attentive Keypoint Identification: Progressive Spatiotemporal Refinement for Video-based Human Pose Estimation AAAI 2026 Augmenting Intra-Modal Understanding in MLLMs for Robust Multimodal Keyphrase Generation AAAI 2026 A Unified Shape-Aware Foundation Model for Time Series Classification AAAI 2026 AutoGameUI: Constructing High-Fidelity GameUI via Multimodal Correspondence Matching AAAI 2026 AV-SSAN: Audio-Visual Selective DOA Estimation Through Explicit Multi-Band Semantic-Spatial Alignment AAAI 2026 Backtrace Mamba: Reviving Critical Temporal Contexts via Hierarchical Memory Compression for Online Action Detection AAAI 2026 BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation AAAI 2026 Being Positive about Negative Queries: Exclusion Aware Multimodal Retrieval using Disentangled Representations WACV 2026 Beyond Coherence: Improving Temporal Consistency and Interpretability in Dynamic Topic Models EACL 2026 Beyond Cosine Similarity: Magnitude-Aware CLIP for No-Reference Image Quality Assessment AAAI 2026 Beyond Local Patterns: Multiscale Inconsistency Learning for Graph Anomaly Detection AAAI 2026 Beyond Neuron-Level Sparsity: Achieving Faithful and Interpretable LLMs with Mixture of Decoders AAAI 2026 Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions AAAI 2026 Beyond Observations: Reconstruction Error-Guided Irregularly Sampled Time Series Representation Learning AAAI 2026 Beyond Real Weights: Hypercomplex Representations for Stable Quantization WACV 2026 Beyond Semantics: How Temporal Biases Shapes Retrieval in Transformer and State-Space Models EACL 2026 Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training Improves Dense Prediction WACV 2026 Beyond Tokens: Concept-Level Training Objectives for LLMs EACL 2026 Beyond Tokens: Dynamic Latent Reasoning via Semantic Residual Refinement AAAI 2026 Biasless Language Models Learn Unnaturally: How LLMs Fail to Distinguish the Possible from the Impossible EACL 2026 BiHiTo: Biomolecular Hierarchy-inspired Tokenization AAAI 2026