← Optimization & Theory

Machine Learning › Optimization & Theory ›

Optimization

14207 directly classified papers

Papers per year

Papers

Confidence-Driven Multi-Scale Model Selection for Cost-Efficient Inference EACL 2026

PIRA: Preference-Oriented Instruction-Tuned Reward Models with Dual Aggregation EACL 2026

ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization EACL 2026

Attribute-Controlled Translation with Preference Optimization EACL 2026

SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph EACL 2026

ORSO QGen: Odds-Ratio Steerable Optimization for Controlling Question Generation EACL 2026

Think Hard Only When Needed: A Hybrid Best-of-N and Beam Search for Efficient Test-Time Compute EACL 2026

POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs EACL 2026

How to Efficiently Explore Noisy Historical Data? Leveraging Corpus Pre-Targeting to Enhance Graph-based RAG EACL 2026

Improving Dialect Robustness in Large Language Models via LoRA and Mixture-of-Experts EACL 2026

Joint Multimodal Preference Optimization for Fine-Grained Visual-Textual Alignment EACL 2026

RB-LoRA: Rank-Balanced Aggregation for Low-Rank Adaptation with Federated Fine-Tuning EACL 2026

Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization EACL 2026

Benchmarking the Energy Savings with Speculative Decoding Strategies EACL 2026

Acceleration of Backpropagation in Linear Layers of Transformer Models Based on Gradient Structure EACL 2026

Unsupervised Text Style Transfer for Controllable Intensity EACL 2026

Optimizer Choice and Calibration for QARiB on Arabic-Script Social Media Offensive Language Detection EACL 2026

Take It All: Ensemble Retrieval for Multimodal Evidence Aggregation EACL 2026

Learning to Ideate for Machine Learning Engineering Agents EACL 2026

ReBPE: Iteratively Improving the Internal Structure of a Structured Tokeniser by Mining its Internal Structure EACL 2026

Poisoned Distillation: Injecting Backdoors into Distilled Datasets Without Raw Data Access AAAI 2026

HGATSolver: A Heterogeneous Graph Attention Solver for Fluid–Structure Interaction AAAI 2026

Parallel Training Time-to-First-Spike Spiking Neural Networks AAAI 2026

DS-ATGO: Dual-Stage Synergistic Learning via Forward Adaptive Threshold and Backward Gradient Optimization for Spiking Neural Networks AAAI 2026

Diversifying Counterattacks: Orthogonal Exploration for Robust CLlP Inference AAAI 2026