{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:36:55Z","timestamp":1780673815671,"version":"3.54.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000105","name":"York University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000105","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227916","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing"],"prefix":"10.1109","author":[{"given":"Boyuan","family":"Chen","sequence":"first","affiliation":[{"name":"New York University,Tandon School of Engineering,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingzhi","family":"Zhu","sequence":"additional","affiliation":[{"name":"New York University,Tandon School of Engineering,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brendan","family":"Dolan-Gavitt","sequence":"additional","affiliation":[{"name":"New York University,Tandon School of Engineering,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Shafique","sequence":"additional","affiliation":[{"name":"New York University Abu Dhabi,eBRAIN Lab, Division of Engineering,Abu Dhabi,UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siddharth","family":"Garg","sequence":"additional","affiliation":[{"name":"New York University,Tandon School of Engineering,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deepseek-coder: When the large language model meets programming \u2013 the rise of code intelligence","author":"Guo","year":"2024"},{"key":"ref2","article-title":"Code llama: Open foundation models for code","author":"Rozi\u00e8re","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1118"},{"key":"ref4","article-title":"Codet: Code generation with generated tests","volume-title":"The Eleventh International Conference on Learning Representations","author":"Chen"},{"key":"ref5","first-page":"46 534","article-title":"Self-refine: Iterative refinement with self-feedback","volume":"36","author":"Madaan","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","article-title":"Self-improvement in language models: The sharpening mechanism","author":"Huang","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1009"},{"key":"ref9","article-title":"Duquant: Distributing outliers via dual transformation makes stronger quantized LLMs","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Lin"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.66"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.808"},{"key":"ref13","article-title":"Fast inference from transformers via speculative decoding","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Leviathan"},{"key":"ref14","article-title":"Large language model cascades with mixture of thought representations for cost-efficient reasoning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yue"},{"key":"ref15","article-title":"Qwen2.5-coder technical report","author":"Hui","year":"2024"},{"key":"ref16","article-title":"Frugalgpt: How to use large language models while reducing cost and improving performance","author":"Chen","year":"2023"},{"key":"ref17","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.3"},{"key":"ref19","article-title":"Gpu cloud pricing","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363447"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.489"},{"key":"ref22","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref23","article-title":"Code alpaca: An instruction-following llama model for code generation","volume-title":"Github repository","author":"Chaudhary","year":"2023"},{"key":"ref24","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021"},{"key":"ref25","article-title":"Program synthesis with large language models","author":"Austin","year":"2021"},{"key":"ref26","article-title":"Measuring coding challenge competence with apps","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","volume":"1","author":"Hendrycks"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref28","article-title":"Accelerate: Training and inference at scale made simple, efficient and adaptable","volume-title":"Github repository","author":"Gugger","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/0717021"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227916.pdf?arnumber=11227916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:11:26Z","timestamp":1763190686000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227916\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227916","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}