Optimization & Theory

LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching ICCV 2025 L-CiteEval: A Suite for Evaluating Fidelity of Long-context Models ACL 2025 LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models ACL 2025 LeanK: Learnable K Cache Channel Pruning for Efficient Decoding EMNLP 2025 Learning a Single Index Model from Anisotropic Data with Vanilla Stochastic Gradient Descent AISTATS 2025 Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval CVPR 2025 Learning Few-Step Diffusion Models by Trajectory Distribution Matching ICCV 2025 Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning ICML 2025 Learning from Streaming Video with Orthogonal Gradients CVPR 2025 Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence AISTATS 2025 Learning Generalized Residual Exchange-Correlation-Uncertain Functional for Density Functional Theory AAAI 2025 Learning Kolmogorov-Arnold Neural Activation Functions by Infinite-Dimensional Optimization L4DC 2025 Learning Phonetic Context-Dependent Viseme for Enhancing Speech-Driven 3D Facial Animation Interspeech 2025 Learning Sparsity for Effective and Efficient Music Performance Question Answering ACL 2025 Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers AAAI 2025 Learn Singularly Perturbed Solutions via Homotopy Dynamics ICML 2025 LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint ACL 2025 LegoMT2: Selective Asynchronous Sharded Data Parallel Training for Massive Neural Machine Translation ACL 2025 Length-Induced Embedding Collapse in PLM-based Models ACL 2025 LESA: Learnable LLM Layer Scaling-Up ACL 2025 Less is More: Efficient Image Vectorization with Adaptive Parameterization CVPR 2025 Less is More: Efficient Model Merging with Binary Task Switch CVPR 2025 Less is More: Empowering GUI Agent with Context-Aware Simplification ICCV 2025 Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions ICLR 2025 Leveraging Attention to Effectively Compress Prompts for Long-Context LLMs AAAI 2025