{"total":29,"rows":[{"id":"2507.23194","title":"Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks","created":"2025-07-31","cited_by_count":32,"area":null},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27,"area":null},{"id":"2507.15887","title":"AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2502.08767","title":"SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence","created":"2025-02-12","cited_by_count":18,"area":null},{"id":"2505.18442","title":"Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2411.01992","title":"Ask, and it shall be given: On the Turing completeness of prompting","created":"2024-11-04","cited_by_count":10,"area":null},{"id":"2502.18489","title":"LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2511.00162","title":"ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus","created":"2025-10-31","cited_by_count":10,"area":null},{"id":"2505.17293","title":"Graph Data Selection for Domain Adaptation: A Model-Free Approach","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2509.19708","title":"Intuition to Evidence: Measuring AI's True Impact on Developer Productivity","created":"2025-09-24","cited_by_count":5,"area":null},{"id":"2510.14756","title":"Pluto: A Benchmark for Evaluating Efficiency of LLM-generated Hardware Code","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2607.19653","title":"PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2508.08332","title":"Energy-Aware Code Generation with LLMs: Benchmarking Small vs. Large Language Models for Sustainable AI Programming","created":"2025-08-10","cited_by_count":2,"area":null},{"id":"2510.25093","title":"Continual Low-Rank Adapters for LLM-based Generative Recommender Systems","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2606.25530","title":"Evaluating LLMs on Real-World Software Performance Optimization","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2504.20673","title":"CoCo-Bench: A Comprehensive Code Benchmark For Multi-task Large Language Model Evaluation","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2509.12530","title":"Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2511.20613","title":"Can Vibe Coding Beat Graduate CS Students? An LLM vs. Human Coding Tournament on Market-driven Strategic Planning","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2602.07256","title":"Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learning","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2605.05267","title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2510.15494","title":"Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2604.05137","title":"EffiPair: Improving the Efficiency of LLM-generated Code with Differential Execution Feedback","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2606.04023","title":"CodegenBench: Can LLMs Write Efficient Code Across Architectures?","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.20554","title":"Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.04577","title":"Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.14839","title":"Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2610.13022","title":"Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13563","title":"Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.19206","title":"DUALVIEW: Leveraging Broad and Output-Specific Evidence for LLM-based Multi-Output Text Regression","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}