← Optimization & Theory
Deep Learning › Optimization & Theory ›

Optimization

1638 directly classified papers

Papers per year

Papers

Answer Convergence as a Signal for Early Stopping in Reasoning EMNLP 2025
Stabilizing Sharpness-Aware Minimization Through A Simple Renormalization Strategy JMLR 2025
Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult JMLR 2025
MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models EMNLP 2025
GAP: a Global Adaptive Pruning Method for Large Language Models EMNLP 2025
Forget What You Know about LLMs Evaluations - LLMs are Like a Chameleon EMNLP 2025
Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning EMNLP 2025
Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization EMNLP 2025
Temporal Scaling Law for Large Language Models EMNLP 2025
Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance EMNLP 2025
AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models EMNLP 2025
Training compute-optimal transformer encoder models EMNLP 2025
ProCut: LLM Prompt Compression via Attribution Estimation EMNLP 2025
Select-then-Route : Taxonomy guided Routing for LLMs EMNLP 2025
Efficient Inference for Large Language Models –Algorithm, Model, and System EMNLP 2025
FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging EMNLP 2025
DTW-Align: Bridging the Modality Gap in End-to-End Speech Translation with Dynamic Time Warping Alignment EMNLP 2025
A statistical perspective on algorithm unrolling models for inverse problems JMLR 2025
LIPIDS: Learning-Based Illumination Planning in Discretized (Light) Space for Photometric Stereo WACV 2025
FreqMoE: Dynamic Frequency Enhancement for Neural PDE Solvers IJCAI 2025
TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training ICCV 2025
MATO: A Model-Agnostic Training Optimization for Aspect Sentiment Triplet Extraction NAACL 2025
Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts NAACL 2025
As easy as PIE: understanding when pruning causes language models to disagree NAACL 2025
The Surprising Effectiveness of Infinite-Width NTKs for Characterizing and Improving Model Training AAAI 2025