{"total":21,"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":"2510.01003","title":"Improving Code Localization with Repository Memory","created":"2025-10-01","cited_by_count":20,"area":null},{"id":"2504.13128","title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2504.15659","title":"VeriCoder: Enhancing LLM-Based RTL Code Generation through Functional Correctness Validation","created":"2025-04-22","cited_by_count":13,"area":null},{"id":"2601.06395","title":"AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages","created":"2026-01-10","cited_by_count":12,"area":null},{"id":"2506.11066","title":"CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2607.27178","title":"DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search","created":"2026-07-29","cited_by_count":6,"area":null},{"id":"2505.24715","title":"CoRet: Improved Retriever for Code Editing","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"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":"2511.05626","title":"LLMs as Packagers of HPC Software","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2601.15339","title":"Lost in Transcription: How Speech-to-Text Errors Derail Code Understanding","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2608.15546","title":"ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2601.19568","title":"Learning Adaptive Parallel Execution for Efficient Code Localization","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.13921","title":"GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2605.04157","title":"FMI_SU_Yotkova_Kastreva at SemEval-2026 Task 13: Lightweight Detection of LLM-Generated Code via Stylometric Signals","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.05251","title":"Identifier-Free Code Embedding Models for Scalable Search","created":"2026-05-05","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":"2607.13311","title":"Finding the Right Tables and Columns: A Benchmark and Corpus-Adaptive Embeddings for SQL Schema Retrieval","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.02967","title":"HyperFL: Query-Adaptive Representation Learning for Software Fault Localization","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.15412","title":"Invariant Pretraining for Robust Code Representations","created":"2026-08-15","cited_by_count":0,"area":null}],"next_cursor":null}