{"list":"other","total":59,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"1807.02811","title":"A Tutorial on Bayesian Optimization","created":"2018-07-08","cited_by_count":744},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"1910.01739","title":"Scalable Global Optimization via Local Bayesian Optimization","created":"2019-10-03","cited_by_count":374},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2109.09831","title":"SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization","created":"2021-09-20","cited_by_count":230},{"id":"1703.01968","title":"Max-value Entropy Search for Efficient Bayesian Optimization","created":"2017-03-06","cited_by_count":206},{"id":"1406.2541","title":"Predictive Entropy Search for Efficient Global Optimization of Black-box Functions","created":"2014-06-10","cited_by_count":204},{"id":"1810.05934","title":"A System for Massively Parallel Hyperparameter Tuning","created":"2018-10-13","cited_by_count":202},{"id":"2410.01560","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","created":"2024-10-02","cited_by_count":200},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177},{"id":"2310.20708","title":"Unexpected Improvements to Expected Improvement for Bayesian Optimization","created":"2023-10-31","cited_by_count":149},{"id":"2103.00349","title":"High-Dimensional Bayesian Optimization with Sparse Axis-Aligned Subspaces","created":"2021-02-27","cited_by_count":141},{"id":"2509.20354","title":"EmbeddingGemma: Powerful and Lightweight Text Representations","created":"2025-09-24","cited_by_count":139},{"id":"1603.08785","title":"COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting","created":"2016-03-29","cited_by_count":138},{"id":"2105.08195","title":"Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement","created":"2021-05-17","cited_by_count":118},{"id":"2109.06716","title":"HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO","created":"2021-09-14","cited_by_count":112},{"id":"2402.02229","title":"Vanilla Bayesian Optimization Performs Great in High Dimensions","created":"2024-02-03","cited_by_count":92},{"id":"1511.05467","title":"Predictive Entropy Search for Multi-objective Bayesian Optimization","created":"2015-11-17","cited_by_count":88},{"id":"2009.01721","title":"Max-value Entropy Search for Multi-Objective Bayesian Optimization with Constraints","created":"2020-09-01","cited_by_count":81},{"id":"2106.06257","title":"HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML","created":"2021-06-11","cited_by_count":75},{"id":"2306.03082","title":"InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models","created":"2023-06-05","cited_by_count":68},{"id":"2109.03670","title":"YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimization","created":"2021-09-08","cited_by_count":62},{"id":"2206.04771","title":"Joint Entropy Search for Maximally-Informed Bayesian Optimization","created":"2022-06-09","cited_by_count":55},{"id":"2304.11468","title":"Increasing the Scope as You Learn: Adaptive Bayesian Optimization in Nested Subspaces","created":"2023-04-22","cited_by_count":52},{"id":"2106.01309","title":"Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domains","created":"2021-05-23","cited_by_count":48},{"id":"2102.03324","title":"GIBBON: General-purpose Information-Based Bayesian OptimisatioN","created":"2021-02-05","cited_by_count":47},{"id":"2210.02905","title":"Joint Entropy Search for Multi-objective Bayesian Optimization","created":"2022-10-06","cited_by_count":45},{"id":"2402.09723","title":"Efficient Prompt Optimization Through the Lens of Best Arm Identification","created":"2024-02-15","cited_by_count":37},{"id":"2405.16122","title":"Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars","created":"2024-05-25","cited_by_count":37},{"id":"2503.04715","title":"Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining","created":"2025-03-06","cited_by_count":34},{"id":"2310.02905","title":"Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers","created":"2023-10-02","cited_by_count":30},{"id":"2010.04153","title":"Olympus: a benchmarking framework for noisy optimization and experiment planning","created":"2020-10-08","cited_by_count":29},{"id":"2506.11300","title":"Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning","created":"2025-06-12","cited_by_count":26},{"id":"2403.02993","title":"Localized Zeroth-Order Prompt Optimization","created":"2024-03-05","cited_by_count":23},{"id":"2502.09198","title":"Understanding High-Dimensional Bayesian Optimization","created":"2025-02-13","cited_by_count":20},{"id":"2012.06932","title":"Warm Starting CMA-ES for Hyperparameter Optimization","created":"2020-12-13","cited_by_count":19},{"id":"2312.00949","title":"Hyperparameter Optimization for Large Language Model Instruction-Tuning","created":"2023-12-01","cited_by_count":17},{"id":"2306.09803","title":"Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization","created":"2023-06-16","cited_by_count":16},{"id":"2508.11953","title":"Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models","created":"2025-08-16","cited_by_count":12},{"id":"2106.04618","title":"EXPObench: Benchmarking Surrogate-based Optimisation Algorithms on Expensive Black-box Functions","created":"2021-06-08","cited_by_count":9},{"id":"2503.21023","title":"Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework","created":"2025-03-26","cited_by_count":9},{"id":"2502.00270","title":"DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks","created":"2025-02-01","cited_by_count":6},{"id":"2411.06710","title":"Model Fusion through Bayesian Optimization in Language Model Fine-Tuning","created":"2024-11-11","cited_by_count":5},{"id":"2602.11171","title":"A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search","created":"2026-01-19","cited_by_count":2}],"next_cursor":null}