← Optimization & Theory
Machine Learning › Optimization & Theory ›

Optimization

14207 directly classified papers

Papers per year

Papers

Mapping the Course for Prompt-based Structured Prediction EACL 2026
KAD: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral EACL 2026
An Empirical Study of Speculative Decoding for Small Language Models EACL 2026
Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning EACL 2026
Offline Preference Optimization via Maximum Marginal Likelihood Estimation EACL 2026
BLUR: A Bi-Level Optimization Approach for LLM Unlearning EACL 2026
How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities EACL 2026
Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs EACL 2026
DRAGOn: Designing RAG On Periodically Updated Corpus EACL 2026
SELENE: Selective and Evidence-Weighted LLM Debating for Efficient and Reliable Reasoning EACL 2026
Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs EACL 2026
Beyond Grid Search: Leveraging Bayesian Optimization for Accelerating RAG Pipeline Optimization EACL 2026
Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives EACL 2026
KETCHUP: K-Step Return Estimation for Sequential Knowledge Distillation EACL 2026
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
Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection AAAI 2026