Deep Learning

Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? A Petroglyph Revisited ACL 2025 Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning? AAAI 2025 Why is children's ASR so difficult? Analyzing children's phonological error patterns using SSL-based phoneme recognizers Interspeech 2025 Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas ICML 2025 Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs ACL 2025 Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding ACL 2025 WiCkeD: A Simple Method to Make Multiple Choice Benchmarks More Challenging ACL 2025 Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg ICML 2025 WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network AAAI 2025 WiGNet: Windowed Vision Graph Neural Network WACV 2025 WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? EMNLP 2025 WildFake: A Large-Scale and Hierarchical Dataset for AI-Generated Images Detection AAAI 2025 Wills Aligner: Multi-Subject Collaborative Brain Visual Decoding AAAI 2025 WINE : Wavelet-Guided GAN Inversion and Editing for High-Fidelity Refinement WACV 2025 Winner-takes-all for Multivariate Probabilistic Time Series Forecasting ICML 2025 Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in QA Agents ACL 2025 Winning ClimateCheck: A Multi-Stage System with BM25, BGE-Reranker Ensembles, and LLM-based Analysis for Scientific Abstract Retrieval ACL 2025 WINS: Winograd Structured Pruning for Fast Winograd Convolution ICCV 2025 WIPES: Wavelet-based Visual Primitives ICCV 2025 WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction ICCV 2025 Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowds IJCAI 2025 WISE: A Framework for Gigapixel Whole-Slide-Image Lossless Compression CVPR 2025 WISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels CVPR 2025 WisPerMed at ArchEHR-QA 2025: A Modular, Relevance-First Approach for Grounded Question Answering on Eletronic Health Records ACL 2025 Wizard of Shopping: Target-Oriented E-commerce Dialogue Generation with Decision Tree Branching ACL 2025