Deep Learning

How Compositional Generalization and Creativity Improve as Diffusion Models are Trained ICML 2025 How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Framework ICLR 2025 How Distributed Collaboration Influences the Diffusion Model Training? A Theoretical Perspective ICML 2025 How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code EMNLP 2025 How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning ICLR 2025 How do autoregressive transformers solve full addition? EMNLP 2025 How Does Critical Batch Size Scale in Pre-training? ICLR 2025 How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis EMNLP 2025 How Does Response Length Affect Long-Form Factuality ACL 2025 How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning? AAAI 2025 How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions CVPR 2025 How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation ICML 2025 How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads EMNLP 2025 How Do Position Encodings Affect Length Generalization? Case Studies On In-Context Function Learning AAAI 2025 How Do Transformers Learn Variable Binding in Symbolic Programs? ICML 2025 How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach ICCV 2025 How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation ACL 2025 How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparison EMNLP 2025 How Far Is Video Generation from World Model: A Physical Law Perspective ICML 2025 How Feature Learning Can Improve Neural Scaling Laws ICLR 2025 How Gradient descent balances features: A dynamical analysis for two-layer neural networks ICLR 2025 How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation EMNLP 2025 How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings ICLR 2025 How many samples are needed to train a deep neural network? ICLR 2025 How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization Guarantees ICML 2025