1.2k citations · 5k across the 41 of their papers we have counts for
41 papers
Technical Report on the CVPR 2026@AdvML Workshop Challenge
Tianyuan Zhang, Zonglei Jing, Jiangfan Liu +47
Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning. This report presents the CVPR 2026@AdvML Workshop Cha…
Large Language Models as Tool Makers
Tianle Cai, Xuezhi Wang, Tengyu Ma +2
Recent research has highlighted the potential of large language models (LLMs) to improve their problem-solving capabilities with the aid of suitable external tools. In our work, we…
Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models
Sheng Shen, Le Hou, Yanqi Zhou +17
Sparse Mixture-of-Experts (MoE) is a neural architecture design that can be utilized to add learnable parameters to Large Language Models (LLMs) without increasing inference cost.…
Symbol tuning improves in-context learning in language models
Jerry Wei, Le Hou, Andrew Lampinen +8
We present symbol tuning - finetuning language models on in-context input-label pairs where natural language labels (e.g., "positive/negative sentiment") are replaced with arbitrar…
Teaching Large Language Models to Self-Debug
Xinyun Chen, Maxwell Lin, Nathanael Schärli +1
Large language models (LLMs) have achieved impressive performance on code generation. However, for complex programming tasks, generating the correct solution in one go becomes chal…
DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection
Yizheng Chen, Zhoujie Ding, Lamya Alowain +2
We propose and release a new vulnerable source code dataset. We curate the dataset by crawling security issue websites, extracting vulnerability-fixing commits and source codes fro…
Larger language models do in-context learning differently
Jerry Wei, Jason Wei, Yi Tay +8
We study how in-context learning (ICL) in language models is affected by semantic priors versus input-label mappings. We investigate two setups-ICL with flipped labels and ICL with…
Large Language Models Can Be Easily Distracted by Irrelevant Context
Freda Shi, Xinyun Chen, Kanishka Misra +5
Large language models have achieved impressive performance on various natural language processing tasks. However, so far they have been evaluated primarily on benchmarks where all…
Benchmarking Language Models for Code Syntax Understanding
Da Shen, Xinyun Chen, Chenguang Wang +2
Pre-trained language models have demonstrated impressive performance in both natural language processing and program understanding, which represent the input as a token sequence wi…
Scaling Instruction-Finetuned Language Models
Hyung Won Chung, Le Hou, Shayne Longpre +32
Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we expl…
Compositional Semantic Parsing with Large Language Models
Andrew Drozdov, Nathanael Schärli, Ekin Akyürek +5
Humans can reason compositionally when presented with new tasks. Previous research shows that appropriate prompting techniques enable large language models (LLMs) to solve artifici…
Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignment
Yujian Gan, Xinyun Chen, Qiuping Huang +1
In text-to-SQL tasks -- as in much of NLP -- compositional generalization is a major challenge: neural networks struggle with compositional generalization where training and test d…
Competition-Level Code Generation with AlphaCode
Yujia Li, David Choi, Junyoung Chung +23
Programming is a powerful and ubiquitous problem-solving tool. Developing systems that can assist programmers or even generate programs independently could make programming more pr…
Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanations
Hui Shi, Sicun Gao, Yuandong Tian +2
Long Short-Term Memory (LSTM) and Transformers are two popular neural architectures used for natural language processing tasks. Theoretical results show that both are Turing-comple…
SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs
Hongyu Ren, Hanjun Dai, Bo Dai +4
Knowledge graphs (KGs) capture knowledge in the form of head--relation--tail triples and are a crucial component in many AI systems. There are two important reasoning tasks on KGs:…
Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization
Yujian Gan, Xinyun Chen, Matthew Purver
Recently, there has been significant progress in studying neural networks for translating text descriptions into SQL queries under the zero-shot cross-domain setting. Despite achie…
Natural SQL: Making SQL Easier to Infer from Natural Language Specifications
Yujian Gan, Xinyun Chen, Jinxia Xie +4
Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation. To bridge this gap, we propose an SQ…
RobustART: Benchmarking Robustness on Architecture Design and Training Techniques
Shiyu Tang, Ruihao Gong, Yan Wang +9
Deep neural networks (DNNs) are vulnerable to adversarial noises, which motivates the benchmark of model robustness. Existing benchmarks mainly focus on evaluating defenses, but th…
A Note on General Statistics of Publicly Accessible Knowledge Bases
Feixiang Wang, Yixiang Fang, Yan Song +2
Knowledge bases are prevalent in various domains and have been widely used in a large number of real applications such as applications in online encyclopedia, social media, biomedi…
Latent Execution for Neural Program Synthesis
Xinyun Chen, Dawn Song, Yuandong Tian
Program synthesis from input-output (IO) examples has been a long-standing challenge. While recent works demonstrated limited success on domain-specific languages (DSL), it remains…
SpreadsheetCoder: Formula Prediction from Semi-structured Context
Xinyun Chen, Petros Maniatis, Rishabh Singh +4
Spreadsheet formula prediction has been an important program synthesis problem with many real-world applications. Previous works typically utilize input-output examples as the spec…
Understanding the Spread of COVID-19 Epidemic: A Spatio-Temporal Point Process View
Shuang Li, Lu Wang, Xinyun Chen +2
Since the first coronavirus case was identified in the U.S. on Jan. 21, more than 1 million people in the U.S. have confirmed cases of COVID-19. This infectious respiratory disease…
Towards Robustness of Text-to-SQL Models against Synonym Substitution
Yujian Gan, Xinyun Chen, Qiuping Huang +4
Recently, there has been significant progress in studying neural networks to translate text descriptions into SQL queries. Despite achieving good performance on some public benchma…
A High-fidelity, Machine-learning Enhanced Queueing Network Simulation Model for Hospital Ultrasound Operations
Yihan Pan, Zhenghang Xu, Jin Guang +10
We collaborate with a large teaching hospital in Shenzhen, China and build a high-fidelity simulation model for its ultrasound center to predict key performance metrics, including…