Papers

R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents (Best Paper)	Daniel D. Johnson, Daniel Tarlow, Christian Walder
SantaCoder: don't reach for the stars! (Best Paper)	Loubna Ben allal, Raymond Li, Denis Kocetkov, Chenghao Mou, Christopher Akiki, Carlos Muñoz Ferrandis, Niklas Muennighoff, Mayank Mishra, Alex Gu, Manan Dey, Logesh Kumar Umapathi, Carolyn Jane Anderson, Yangtian Zi, Hailey Schoelkopf, Sergey Troshin, Dmitry Abulkhanov, Michael Lappert, Francesco De Toni, Qian Liu, Shamik Bose, Terry Yue Zhuo, Ian Yu, Paulo Villegas, Bernardo Garcia del Rio, Marco Zocca, Sourab Mangrulkar, Urvashi Bhattacharyya, Joel Lamy-Poirier, Huu Nguyen, David Lansky, Danish Contractor, Jia LI, Dzmitry Bahdanau, Yacine Jernite, Sean Hughes, Daniel Fried, Arjun Guha, Harm de Vries, Leandro Von Werra
Conversational Automated Program Repair (Spotlight)	Chunqiu Steven Xia, Lingming Zhang
CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code (Spotlight)	Shuyan Zhou, Uri Alon, Sumit Agarwal, Graham Neubig
A Generic Prompt for an LLM that enables NL-to-SQL across Domains and Compositions	Aseem Arora, Shabbirhussain Bhaisaheb, Manasi Patwardhan, Lovekesh Vig, Gautam Shroff
“If it’s what I wanted that’s great, but if it’s not, I just wasted time”: Examining the perceived costs/benefits of ML-enhanced developer tooling.	Ambar Murillo, Sarah D'Angelo, Quinn Madison, Iris Chu, Andrew Macvean
DisPer: End-to-End Neural Permutation Program Synthesis	Peter Belcak, Roger Wattenhofer
Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs	Guan-Ting Liu, En-Pei Hu, Pu-Jen Cheng, Hung-yi Lee, Shao-Hua Sun
Multilingual Code Retrieval Without Paired Data: A New Benchmark and Experiments	Joao Monteiro, Torsten Scholak, Virendra Mehta, David Vazquez, Christopher Pal
ReCode: Robustness Evaluation of Code Generation Models	Shiqi Wang, Zheng Li, Haifeng Qian, Chenghao Yang, Zijian Wang, Mingyue Shang, Varun Kumar, Samson Tan, Baishakhi Ray, Parminder Bhatia, Ramesh Nallapati, Murali Krishna Ramanathan, Dan Roth, Bing Xiang
Leveraging Static Analysis for Bug Repair	Ruba Mutasim, Gabriel Synnaeve, David Pichardie, Baptiste Roziere
CONTRACLM: Contrastive Learning For Causal Language Model	Nihal Jain, Dejiao Zhang, Wasi Uddin Ahmad, Zijian Wang, Feng Nan, Xiaopeng Li, Ming Tan, Ramesh Nallapati, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, Bing Xiang
BigIssue: A Realistic Bug Localization Benchmark	Paul Kassianik, Erik Nijkamp, Bo Pang, Yingbo Zhou, Caiming Xiong
ObSynth: An Interactive Synthesis System for Generating Object Models from Natural Language Specifications	Alex Gu, Tamara Mitrovska, Daniela Velez, Jacob Andreas, Armando Solar-Lezama
TASTY: A TRANSFORMER BASED APPROACH TO SPACE AND TIME COMPLEXITY	Kaushik Moudgalya, Ankit Ramakrishnan, Vamsikrishna Chemudupati, Xing Han Lu
Semantic Prefixes as an Auxiliary Target for Code Understanding and Generation	Kechen Qin, Fan Yang, Kai-Wei Chang, Prashan Wanigasekara, Xinyue Liu, Chengwei Su, Emre Barut
Learning Performance-Improving Code Edits	Aman Madaan, Alexander G Shypula, Uri Alon, Milad Hashemi, Parthasarathy Ranganathan, Yiming Yang, Graham Neubig, Amir Yazdanbakhsh
CodeGen2: Lessons for Training LLMs on Programming and Natural Languages	Erik Nijkamp, Hiroaki Hayashi, Caiming Xiong, Silvio Savarese, Yingbo Zhou
ScriptoriumWS: A Code Generation Assistant for Weak Supervision	Tzu-Heng Huang, Catherine Cao, Spencer Schoenberg, Harit Vishwakarma, Nicholas Roberts, Frederic Sala
SYNTHESIS OF MATHEMATICAL PROGRAMS FROM NATURAL LANGUAGE SPECIFICATIONS	Ganesh Prasath Ramani, Shirish Karande
Explicit Knowledge Transfer for Weakly-Supervised Code Generation	Zhangir Azerbayev, Ansong Ni, Hailey Schoelkopf, Dragomir Radev
XLCOST: A BENCHMARK DATASET FOR CROSS- LINGUAL CODE INTELLIGENCE	Ming Zhu, Aneesh Jain, Karthik Suresh, Roshan Ravindran, Sindhu Tipirneni, Chandan K. Reddy
APerfCode: Auto Conversion to Performant Code	Sharod Roy Choudhury, Mayank Mishra, Rekha Singhal, Sirish Karande