Representation Learning

RUBY: An Effective Framework for Multi-Constraint Multi-Hop Question Generation ACL 2025 RuCCoD: Towards Automated ICD Coding in Russian EMNLP 2025 Run Like a Neural Network, Explain Like k-Nearest Neighbor IJCAI 2025 S²DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion AAAI 2025 S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting CVPR 2025 S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modeling ACL 2025 S3 - Semantic Signal Separation ACL 2025 S4M: S4 for multivariate time series forecasting with Missing values ICLR 2025 SA-DETR:Span Aware Detection Transformer for Moment Retrieval COLING 2025 SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability ICML 2025 SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models EMNLP 2025 SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders ICML 2025 SAGEPhos: Sage Bio-Coupled and Augmented Fusion for Phosphorylation Site Detection ICLR 2025 Samba: A Unified Mamba-based Framework for General Salient Object Detection CVPR 2025 SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformity CVPR 2025 Sample-specific Noise Injection for Diffusion-based Adversarial Purification ICML 2025 SAND: One-Shot Feature Selection with Additive Noise Distortion ICML 2025 SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE CVPR 2025 SARA: Salience-Aware Reinforced Adaptive Decoding for Large Language Models in Abstractive Summarization ACL 2025 SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery AAAI 2025 SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders ICCV 2025 SAVOR: Skill Affordance Learning from Visuo-Haptic Perception for Robot-Assisted Bite Acquisition CoRL 2025 Scalable Image Tokenization with Index Backpropagation Quantization ICCV 2025 Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment ICML 2025 Scalable Quantum-Inspired Optimization Through Dynamic Qubit Compression AAAI 2025