← Optimization & Theory
Deep Learning › Optimization & Theory ›

Optimization

1638 directly classified papers

Papers per year

Papers

Boost Your Human Image Generation Model via Direct Preference Optimization CVPR 2025
Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales CVPR 2025
Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation CVPR 2025
Finding Local Diffusion Schrodinger Bridge using Kolmogorov-Arnold Network CVPR 2025
Balanced Rate-Distortion Optimization in Learned Image Compression CVPR 2025
Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeoff ACL 2025
ECoRAG: Evidentiality-guided Compression for Long Context RAG ACL 2025
Add-One-In: Incremental Sample Selection for Large Language Models via a Choice-Based Greedy Paradigm EMNLP 2025
Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models ACL 2025
HD-PiSSA: High-Rank Distributed Orthogonal Adaptation EMNLP 2025
Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification EMNLP 2025
Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence EMNLP 2025
AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training EMNLP 2025
EvoAgentX: An Automated Framework for Evolving Agentic Workflows EMNLP 2025
Structure Trumps Size: Rethinking Data Quality for LLM Reasoning EMNLP 2025
Mitigating Sequential Dependencies: A Survey of Algorithms and Systems for Generation-Refinement Frameworks in Autoregressive Models EMNLP 2025
Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding EMNLP 2025
PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models EMNLP 2025
Single layer tiny Co4 outpaces GPT-2 and GPT-BERT EMNLP 2025
DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability EMNLP 2025
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training CVPR 2025
Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation CVPR 2025
TKG-DM: Training-free Chroma Key Content Generation Diffusion Model CVPR 2025
Identifying and Mitigating Position Bias of Multi-image Vision-Language Models CVPR 2025
LESA: Learnable LLM Layer Scaling-Up ACL 2025