Representation Learning

Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization ICCV 2025 SDAS: Semantic Data Acquisition System for Minimizing Redundancy and Maximizing Diversity AAAI 2025 SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations ICML 2025 SEAL: Scaling to Emphasize Attention for Long-Context Retrieval ACL 2025 SEAL: Semantic Attention Learning for Long Video Representation CVPR 2025 SEAL: Structure and Element Aware Learning Improves Long Structured Document Retrieval EMNLP 2025 Search-o1: Agentic Search-Enhanced Large Reasoning Models EMNLP 2025 SECodec: Structural Entropy-based Compressive Speech Representation Codec for Speech Language Models AAAI 2025 SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding ICML 2025 Secret Lies in Color: Enhancing AI-Generated Images Detection with Color Distribution Analysis CVPR 2025 Seeing Beyond Noise: Joint Graph Structure Evaluation and Denoising for Multimodal Recommendation AAAI 2025 Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding ICCV 2025 Seeing Through Words, Speaking Through Pixels: Deep Representational Alignment Between Vision and Language Models EMNLP 2025 Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection CVPR 2025 Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era ACL 2025 SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning ICML 2025 SEKE: Specialised Experts for Keyword Extraction EMNLP 2025 Self-Attentive Spatio-Temporal Calibration for Precise Intermediate Layer Matching in ANN-to-SNN Distillation AAAI 2025 Self-Discriminative Modeling for Anomalous Graph Detection ICML 2025 SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence ACL 2025 Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning CVPR 2025 Self-Explainable Graph Transformer for Link Sign Prediction AAAI 2025 Self Knowledge-Tracing for Tool Use (SKT-Tool): Helping LLM Agents Understand Their Capabilities in Tool Use NAACL 2025 Self-Retrieval from Distant Contexts for Document-Level Machine Translation EMNLP 2025 Self-Supervised Collaborative Information Bottleneck for Text Readability Assessment AAAI 2025