{"total":24,"rows":[{"id":"2506.18902","title":"jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval","created":"2025-06-23","cited_by_count":76,"area":null},{"id":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32,"area":null},{"id":"2505.07849","title":"SweRank: Software Issue Localization with Code Ranking","created":"2025-05-07","cited_by_count":20,"area":null},{"id":"2506.22419","title":"The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements","created":"2025-06-27","cited_by_count":15,"area":null},{"id":"2603.11863","title":"CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges","created":"2026-03-12","cited_by_count":9,"area":null},{"id":"2506.11059","title":"CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2507.08983","title":"Exploiting Leaderboards for Large-Scale Distribution of Malicious Models","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2505.12925","title":"CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2512.21332","title":"C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2507.12674","title":"ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2603.22008","title":"On the Challenges and Opportunities of Learned Sparse Retrieval for Code","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2604.06793","title":"Evaluating Repository-level Software Documentation via Question Answering and Feature-Driven Development","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2604.24814","title":"SWE-QA: A Dataset and Benchmark for Complex Code Understanding","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2607.15205","title":"MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2505.19757","title":"CIDRe: A Reference-Free Multi-Aspect Criterion for Code Comment Quality Measurement","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2508.08545","title":"OmniLLP: Enhancing LLM-based Log Level Prediction with Context-Aware Retrieval","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2512.10393","title":"Cross-modal Retrieval Models for Stripped Binary Analysis","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2503.05315","title":"LoRACode: LoRA Adapters for Code Embeddings","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2508.06734","title":"Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmark","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2510.27675","title":"On the Difficulty of Selecting Few-Shot Examples for Effective LLM-based Vulnerability Detection","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2605.08299","title":"Do not copy and paste! Rewriting strategies for code retrieval","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.27787","title":"Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.27401","title":"Recall Before Rerank: Benchmarking Deep Learning Models for Large-Scale Code-to-Code Retrieval","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2610.19157","title":"DivAlgo: A systematic evaluation of algorithmic diversity for code generation models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}