Deep Learning

The Superposition of Diffusion Models Using the Itô Density Estimator ICLR 2025 The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training ICML 2025 The Surprising Effectiveness of Infinite-Width NTKs for Characterizing and Improving Model Training AAAI 2025 The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMs EMNLP 2025 The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation Project ACL 2025 The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training ICML 2025 The Unreasonable Ineffectiveness of the Deeper Layers ICLR 2025 The VampPrior Mixture Model AISTATS 2025 The Visual Counter Turing Test (VCT²): A Benchmark for Evaluating AI-Generated Image Detection and the Visual AI Index (V_AI) IJCNLP 2025 The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence ACL 2025 THGNets: Constrained Temporal Hypergraphs and Graph Neural Networks in Hyperbolic Space for Information Diffusion Prediction AAAI 2025 Thickness-aware E(3)-Equivariant 3D Mesh Neural Networks ICML 2025 Thinking Fast and Slow: Robust Speech Recognition via Deep Filter-Tuning Interspeech 2025 Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Interspeech 2025 Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues AAAI 2025 Thinking Out Loud: Do Reasoning Models Know When They’re Right? EMNLP 2025 Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series EMNLP 2025 Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model EMNLP 2025 Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking ACL 2025 ThinkQE: Query Expansion via an Evolving Thinking Process EMNLP 2025 Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair EMNLP 2025 ThinkSLM: Towards Reasoning in Small Language Models EMNLP 2025 Think Twice: Test-Time Reasoning for Robust CLIP Zero-Shot Classification ICCV 2025 Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields CVPR 2025 THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation ACL 2025