← Optimization & Theory
Deep Learning › Optimization & Theory ›

Optimization

1638 directly classified papers

Papers per year

Papers

LegoMT2: Selective Asynchronous Sharded Data Parallel Training for Massive Neural Machine Translation ACL 2025
Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeoff ACL 2025
ECoRAG: Evidentiality-guided Compression for Long Context RAG ACL 2025
Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models ACL 2025
Hierarchical Speculative Decoding with Dynamic Window NAACL 2025
Position Really Matters: Towards a Holistic Approach for Prompt Tuning NAACL 2025
Integrating Independent Layer-Wise Rank Selection with Low-Rank SVD Training for Model Compression: A Theory-Driven Approach IJCAI 2025
A Priori Estimation of the Approximation, Optimization and Generalization Errors of Random Neural Networks for Solving Partial Differential Equations IJCAI 2025
Accelerating Adversarial Training on Under-Utilized GPU IJCAI 2025
Dual-Balancing for Physics-Informed Neural Networks IJCAI 2025
TKG-DM: Training-free Chroma Key Content Generation Diffusion Model CVPR 2025
Dataset Distillation with Neural Characteristic Function: A Minmax Perspective CVPR 2025
WINS: Winograd Structured Pruning for Fast Winograd Convolution ICCV 2025
Towards Performance Consistency in Multi-Level Model Collaboration ICCV 2025
FedAGC: Federated Continual Learning with Asymmetric Gradient Correction ICCV 2025
PoseAnchor: Robust Root Position Estimation for 3D Human Pose Estimation ICCV 2025
MH-LVC: Multi-Hypothesis Temporal Prediction for Learned Conditional Residual Video Coding ICCV 2025
FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization ICCV 2025
QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models EMNLP 2025
MUZO: Leveraging Multiple Queries and Momentum for Zeroth-Order Fine-Tuning of Large Language Models EMNLP 2025
CoMMIT: Coordinated Multimodal Instruction Tuning EMNLP 2025
Calibration Across Layers: Understanding Calibration Evolution in LLMs EMNLP 2025
FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference EMNLP 2025
Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation EMNLP 2025
TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training ICCV 2025