Representation Learning

SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints AAAI 2025 SUWMIT at BioLaySumm2025: Instruction-based Summarization with Contrastive Decoding ACL 2025 SVRMamba: Slice-to-Volume Reconstruction from Multiple MRI Stacks with Slice Sequence Guided Mamba AAAI 2025 SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution ACL 2025 SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Engine AAAI 2025 SYNC: A Synthetic Long-Context Understanding Benchmark for Controlled Comparisons of Model Capabilities EMNLP 2025 Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation CVPR 2025 Synthetic Data in the Era of Large Language Models ACL 2025 T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation CVPR 2025 TablePilot: Recommending Human-Preferred Tabular Data Analysis with Large Language Models ACL 2025 TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection CVPR 2025 TA-RIR: Topology-Aware Neural Modeling of Acoustic Propagation for Room Impulse Response Synthesis Interspeech 2025 Task-Driven Discrete Representation Learning AISTATS 2025 Temporal Information Retrieval via Time-Specifier Model Merging ACL 2025 Tensor Decomposition Based Memory-Efficient Incremental Learning ICML 2025 Tensor-Var: Efficient Four-Dimensional Variational Data Assimilation ICML 2025 Textagon: Boosting Language Models with Theory-guided Parallel Representations ACL 2025 Textured Mesh Saliency: Bridging Geometry and Texture for Human Perception in 3D Graphics AAAI 2025 TFDP: Token-Efficient Disparity Audits for Autoregressive LLMs via Single-Token Masked Evaluation EMNLP 2025 The Hidden Attention of Mamba Models ACL 2025 The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model Inference ICML 2025 The Knowledge Microscope: Features as Better Analytical Lenses than Neurons ACL 2025 The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure EMNLP 2025 The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension Reduction ICML 2025 There’s No Such Thing as Simple Reasoning for LLMs ACL 2025