Open Access. Powered by Scholars. Published by Universities.®

Programming Languages and Compilers Commons™

Open Access. Powered by Scholars. Published by Universities.®

Series

Discipline
Institution
Keyword
Publication Year
Publication
File Type

Articles 1 - 30 of 1424

Full-Text Articles in Programming Languages and Compilers

Larger Is Not Always Better: Exploring Small Open-Source Language Models In Logging Statement Generation, Renyi Zhong, Yichen Li, Guangba Yu, Wenwei Gu, Jinxi Kuang, Yintong Huo, Michael R. Lyu Jul 2026

Larger Is Not Always Better: Exploring Small Open-Source Language Models In Logging Statement Generation, Renyi Zhong, Yichen Li, Guangba Yu, Wenwei Gu, Jinxi Kuang, Yintong Huo, Michael R. Lyu

Research Collection School Of Computing and Information Systems

Developers use logging statements to create logs that document system behavior and aid in software maintenance. As such, high-quality logging is essential for effective maintenance; however, manual logging often leads to errors and inconsistency. Recent methods emphasize using large language models (LLMs) for automated logging statement generation, but these present privacy and resource issues, hindering their suitability for enterprise use. This paper presents the first large-scale empirical study evaluating small open-source language models (SOLMs) for automated logging statement generation. We evaluate four prominent SOLMs using various prompt strategies and parameter-efficient fine-tuning techniques, such as Low-Rank Adaptation (LoRA) and Retrieval-Augmented Generation …

Go to article

Llms In Compiler Construction, Raffi Khatchadourian May 2026

Llms In Compiler Construction, Raffi Khatchadourian

Open Educational Resources

These lecture slides survey the use of large language models (LLMs) in compiler construction for a graduate compiler course (CSc 81010). They situate LLMs across the compiler pipeline and examine representative work: foundation models trained on LLVM IR and assembly (Meta's LLM Compiler), LLM-driven code optimization, binary decompilation (LLM4Decompile), and LLM-assisted automated refactoring—alongside the challenges of applying probabilistic models to tasks that demand correctness. The slides are a self-contained HTML (W3C Slidy) deck with editable Pandoc Markdown source. Part of a two-session unit on advanced compiler topics; see also "Deep Learning Compilers."

Go to article

Deep Learning Compilers, Raffi Khatchadourian May 2026

Deep Learning Compilers, Raffi Khatchadourian

Open Educational Resources

These lecture slides introduce deep learning compilers for a graduate compiler-construction course (CSc 81010). Building on the classical compiler pipeline, they show how modern machine-learning systems compile tensor programs: static tensor and type analysis (illustrated by a WALA/Ariadne-based refactoring of imperative TensorFlow code to graph mode), MLIR-based end-to-end compilation with IREE, and the PyTorch 2.x stack—TorchDynamo graph capture, AOTAutograd, PrimTorch operator decomposition, and TorchInductor lowering to Triton (GPU) and C++/OpenMP (CPU). The slides are a self-contained HTML (W3C Slidy) deck with editable Pandoc Markdown source. Part of a two-session unit on advanced compiler topics; see also "LLMs in Compiler Construction."

Go to article

Quantitative Bounds On Resource Usage Of Probabilistic Programs, Krishnendu Chatterjee, Amir Kafshdar Goharshady, Tobias Meggendorfer, Dorde Zikelic May 2026

Quantitative Bounds On Resource Usage Of Probabilistic Programs, Krishnendu Chatterjee, Amir Kafshdar Goharshady, Tobias Meggendorfer, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Cost analysis, also known as resource usage analysis, is the task of finding bounds on the total cost of a program and is a well-studied problem in static analysis. In this work, we consider two classical quantitative problems in cost analysis for probabilistic programs. The first problem is to find a bound on the expected total cost of the program. This is a natural measure for the resource usage of the program and can also be directly applied to average-case runtime analysis. The second problem asks for a tail bound, i.e. ‍given a threshold t the goal is to find …

Go to article

Generation Of Elaborated, Targeted And Effective Feedback For Novice Programmers Using Llm, Hua Leong Fwa May 2026

Generation Of Elaborated, Targeted And Effective Feedback For Novice Programmers Using Llm, Hua Leong Fwa

Research Collection School Of Computing and Information Systems

Programming errors and misconceptions are pervasive in novice programmers which causes difficulty in the learning of computer programming. Large Language Models (LLMs), with their ability to comprehend and generate programming codes have shown promising results in the automatic identification of errors. This can potentially benefit student programmers by providing them with timely formative feedback at efficiencies and scale that were not attainable previously. In this study, we leveraged an LLM - OpenAI o4-mini for the generation of elaborated, targeted feedback for novice programmers across PHP and JavaScript exercises. We contend that the feedback needs to be effective and targeted other …

Go to article

A New Tool For Handling Multiracial And Multi-Identity Data In Health Research, Gabriel J. Merrin Feb 2026

A New Tool For Handling Multiracial And Multi-Identity Data In Health Research, Gabriel J. Merrin

Population Health Research Brief Series

When surveys ask about race or ethnicity, a growing number of Americans select more than one category. The multiracial population now represents over 10% of the U.S. population and is the fastest growing racial group in the country. Yet researchers routinely collapse these individuals into an “other race” category for statistical analysis, rendering specific subgroups invisible. This brief introduces CATAcode, a free software tool that helps researchers systematically explore, document, and prepare check-all-that-apply demographic data for statistical modeling. In a demonstration with over 8,000 high school students, CATAcode revealed 85 distinct racial identity combinations from just eight response options. The …

Go to article

Oer Review For Open Programming: Java I - Creating An Oer Textbook For Programming Fundamentals, Peter Arsenault Jan 2026

Oer Review For Open Programming: Java I - Creating An Oer Textbook For Programming Fundamentals, Peter Arsenault

Open Educational Resources Publications

This report describes the creation and implementation of a seven‑chapter Open Educational Resource (OER) for Bentley University’s CS 180 – Programming Fundamentals course, developed from the author’s teaching notes, custom examples, and course materials from Fall 2024. The project aimed to provide current, accessible, digital‑first learning resources aligned with modern programming tools, supported by generative‑AI editing in NotebookLM and open‑source formatting tools such as pandoc and Marp. Implemented during Fall 2025, the OER received highly positive student feedback, particularly regarding its clarity, accessibility, and cost savings, and it is slated for further refinement—including updates for Java 25, expanded examples, and …

Go to article

Do Developers Read Type Information? An Eye-Tracking Study On Typescript, Samuel W. Flint, Robert Dyer, Bonita Sharif Jan 2026

Do Developers Read Type Information? An Eye-Tracking Study On Typescript, Samuel W. Flint, Robert Dyer, Bonita Sharif

Research & Publications

Statically-annotated types have been shown to aid developers in a number of programming tasks, and this benefit holds true even when static type checking is not used. It is hypothesized that this is because developers use type annotations as in-code documentation. In this study, we aim to provide evidence that developers use type annotations as in-code documentation. Understanding this hypothesized use will help to understand how, and in what contexts, developers use type information; additionally, it may help to design better development tools and inform educational decisions. To provide this evidence, we conduct an eye tracking study with 26 undergraduate …

Go to article

Automatic Generation Of Introductory Programming Exercises With Large Language Models, Nguyen Binh Duong Ta, Hua Gia Phuc Nguyen, Gottipati Swapna Jan 2026

Automatic Generation Of Introductory Programming Exercises With Large Language Models, Nguyen Binh Duong Ta, Hua Gia Phuc Nguyen, Gottipati Swapna

Research Collection School Of Computing and Information Systems

Despite recent advances in code generation made possible by large language models (LLMs), programming is still an essential skill that computing students need to master now and in the foreseeable future. In learning programming, frequent practices with exercises set at an appropriate difficulty and knowledge level is of crucial importance for students. However, it’s not a trivial task for instructors to create many good quality exercises customized for each student. Programming problems found on Internet sources such as LeetCode are mostly too challenging for novice programmers with no prior coding knowledge. Recent work in AI-enabled education has been leveraging LLMs …

Go to article

Backdoorllm: A Comprehensive Benchmark For Backdoor Attacks And Defenses On Large Language Models, Yige Li, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Jun Sun Dec 2025

Backdoorllm: A Comprehensive Benchmark For Backdoor Attacks And Defenses On Large Language Models, Yige Li, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Jun Sun

Research Collection School Of Computing and Information Systems

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce adversaryspecified outputs. While prior research has predominantly focused on backdoor risks in vision and classification settings, the vulnerability of LLMs in open-ended text generation remains underexplored. To fill this gap, we introduce BackdoorLLM1 , the first comprehensive benchmark for systematically evaluating backdoor threats in text-generation LLMs. BackdoorLLM provides: (i) a unified repository of benchmarks with a standardized training and evaluation pipeline; (ii) a diverse suite of …

Go to article

A Learning‑Augmented Dynamic Programming Approach For Orienteering Problem With Time Windows, Guansheng Peng, Lining Xing, Fuyan Song Ma, Aldy Gunawan, Aldy Gunawan Dec 2025

A Learning‑Augmented Dynamic Programming Approach For Orienteering Problem With Time Windows, Guansheng Peng, Lining Xing, Fuyan Song Ma, Aldy Gunawan, Aldy Gunawan

Research Collection School Of Computing and Information Systems

Recent years have witnessed a surge of interest in solving combinatorial optimization problems (COPs) using machine learning techniques. Motivated by this trend, we propose a learning-augmented exact approach for tackling an NP-hard COP, the Orienteering Problem with Time Windows, which aims to maximize the total score collected by visiting a subset of vertices in a graph within their time windows. Traditional exact algorithms rely heavily on domain expertise and meticulous design, making it hard to achieve further improvements. By leveraging deep learning models to learn effective relaxations of problem restrictions from data, our approach enables significant performance gains in an …

Go to article

The Rise Of Parameter Specialization For Knowledge Storage In Large Language Models, Yihuai Hong, Yiran Zhao, Wei Tang, Yang Deng, Yu Rong, Wenxuan Zhang Dec 2025

The Rise Of Parameter Specialization For Knowledge Storage In Large Language Models, Yihuai Hong, Yiran Zhao, Wei Tang, Yang Deng, Yu Rong, Wenxuan Zhang

Research Collection School Of Computing and Information Systems

Over time, a growing wave of large language models from various series has been introduced to the community. Researchers are striving to maximize the performance of language models with constrained parameter sizes. However, from a microscopic perspective, there has been limited research on how to better store knowledge in model parameters, particularly within MLPs, to enable more effective utilization of this knowledge by the model. In this work, we analyze twenty publicly available open-source large language models to investigate the relationship between their strong performance and the way knowledge is stored in their corresponding MLP parameters. Our findings reveal that …

Go to article

A Partition Cover Approach To Tokenization, Jia Peng Lim, Shawn Tan, Davin Choo, Hady Wirawan Lauw Dec 2025

A Partition Cover Approach To Tokenization, Jia Peng Lim, Shawn Tan, Davin Choo, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Tokenization is the process of encoding strings into tokens of a fixed vocabulary size, and is widely utilized in Natural Language Processing applications. The leading tokenization algorithm today is Byte Pair Encoding (BPE), which formulates the tokenization problem as a compression problem and tackles it by performing sequences of merges. In this work, we formulate tokenization as an optimization objective, show that it is NP-hard via a simple reduction from vertex cover, and propose a polynomial-time greedy algorithm GreedTok. Our formulation naturally relaxes to the well-studied weighted maximum coverage problem which has a simple -approximation algorithm GreedWMC. Through empirical evaluations …

Go to article

When Less Language Is More: Language-Reasoning Disentanglement Makes Llms Better Multilingual Reasoners, Weixiang Zhao, Jiahe Guo, Yang Deng, Tongtong Wu, Wenxuan Zhang, Yulin Hu, Xingyu Sui, Yanyan Zhao, Wanxiang Che, Bing Qin, Tat-Seng Chua, Ting Liu Dec 2025

When Less Language Is More: Language-Reasoning Disentanglement Makes Llms Better Multilingual Reasoners, Weixiang Zhao, Jiahe Guo, Yang Deng, Tongtong Wu, Wenxuan Zhang, Yulin Hu, Xingyu Sui, Yanyan Zhao, Wanxiang Che, Bing Qin, Tat-Seng Chua, Ting Liu

Research Collection School Of Computing and Information Systems

Multilingual reasoning remains a significant challenge for large language models (LLMs), with performance disproportionately favoring high-resource languages. Drawing inspiration from cognitive neuroscience, which suggests that human reasoning functions largely independently of language processing, we hypothesize that LLMs similarly encode reasoning and language as separable components that can be disentangled to enhance multilingual reasoning. To evaluate this, we perform a causal intervention by ablating language-specific representations at inference time. Experiments on 10 open-weight LLMs spanning 11 typologically diverse languages show that this language-specific ablation consistently boosts multilingual reasoning performance. Layer-wise analyses further confirm that language and reasoning representations can be effectively …

Go to article

Speculative Automated Refactoring Of Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian Ph.D., Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja Nov 2025

Speculative Automated Refactoring Of Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian Ph.D., Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code---supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the "best of both worlds," using them effectively requires subtle considerations. Our key insight is that, while DL programs typically execute sequentially, hybridizing imperative DL code resembles parallelizing sequential code in traditional systems. Inspired by this, we …

Go to article

Speculative Automated Refactoring Of Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian Ph.D., Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja Nov 2025

Speculative Automated Refactoring Of Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian Ph.D., Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code---supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the "best of both worlds," using them effectively requires subtle considerations. Our key insight is that, while DL programs typically execute sequentially, hybridizing imperative DL code resembles parallelizing sequential code in traditional systems. Inspired by this, we …

Go to article

Speculative Automated Refactoring Of Imperative Deep Learning Programs To Graph Execution, Raffi T. Khatchadourian Ph.D., Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja Nov 2025

Speculative Automated Refactoring Of Imperative Deep Learning Programs To Graph Execution, Raffi T. Khatchadourian Ph.D., Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code---supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the "best of both worlds," using them effectively requires subtle considerations. Our key insight is that, while DL programs typically execute sequentially, hybridizing imperative DL code resembles parallelizing sequential code in traditional systems. Inspired by this, we …

Go to article

Do Code Semantics Help? A Comprehensive Study On Execution Trace-Based Information For Code Large Language Models, Jian Wang, Xiaofei Xie, Qiang Hu, Shangqing Liu, Yi Li Nov 2025

Do Code Semantics Help? A Comprehensive Study On Execution Trace-Based Information For Code Large Language Models, Jian Wang, Xiaofei Xie, Qiang Hu, Shangqing Liu, Yi Li

Research Collection School Of Computing and Information Systems

Code Large Language Models (Code LLMs) have opened a new era in programming with their impressive capabilities. However, recent research has revealed critical limitations in their ability to reason about runtime behavior and understand the actual functionality of programs, which poses significant challenges for their post-training and practical deployment. Specifically, Code LLMs encounter two principal issues: (1) a lack of proficiency in reasoning about program execution behavior, as they struggle to interpret what programs actually do during runtime, and (2) inconsistent and fragmented representation of semantic information, such as execution traces, across existing methods, which hinders their ability to generalize …

Go to article

Mmlu-Prox: A Multilingual Benchmark For Advanced Large Language Model Evaluation, Weihao Xuan, Et. Al. Nov 2025

Mmlu-Prox: A Multilingual Benchmark For Advanced Large Language Model Evaluation, Weihao Xuan, Et. Al.

Research Collection School Of Computing and Information Systems

Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities. This dual limitation makes it challenging to assess LLMs’ performance in the multilingual setting comprehensively. To fill this gap, we introduce MMLU-ProX, a comprehensive benchmark covering 29 languages, built on an English benchmark. Each language version consists of 11,829 identical questions, enabling direct cross-lingual comparisons. Additionally, to meet efficient evaluation needs, we provide a lite version containing 658 questions per language. To ensure the high quality of MMLU-ProX, we employ a rigorous development process that involves …

Go to article

Chain Of Strategy Optimization Makes Large Language Models Better Emotional Supporter, Weixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu Nov 2025

Chain Of Strategy Optimization Makes Large Language Models Better Emotional Supporter, Weixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu

Research Collection School Of Computing and Information Systems

The growing emotional stress in modern society has increased the demand for Emotional Support Conversations (ESC). While Large Language Models (LLMs) show promise for ESC, they face two key challenges: (1) low strategy selection accuracy, and (2) preference bias, limiting their adaptability to users’ emotional needs. Existing supervised fine-tuning (SFT) struggles to address these issues, as it rigidly trains models on single gold-standard responses without modeling nuanced strategy trade-offs. To overcome these limitations, we propose a novel two-stage framework that optimizes strategy selection preferences at each dialogue turn. We first leverage Monte Carlo Tree Search to construct ESC-Pro, a high-quality …

Go to article

Envisioning Future Interactive Web Development: Editing Webpage With Natural Language, Truong Hai Dang, Jingyu Xiao, Yintong Huo Nov 2025

Envisioning Future Interactive Web Development: Editing Webpage With Natural Language, Truong Hai Dang, Jingyu Xiao, Yintong Huo

Research Collection School Of Computing and Information Systems

The evolution of web applications relies on iterative code modifications, a process that is traditionally manual and time-consuming. While Large Language Models (LLMs) can generate UI code, their ability to edit existing code from new design requirements (e.g., ”center the logo”) remains a challenge. This is largely due to the absence of large-scale, high-quality tuning data to align model performance with human expectations. In this paper, we introduce a novel, automated data generation pipeline that uses LLMs to synthesize a high-quality fine-tuning dataset for web editing, named Instruct4Edit. Our approach generates diverse instructions, applies the corresponding code modifications, and performs …

Go to article

One Planner To Guide Them All! Learning Adaptive Conversational Planners For Goal-Oriented Dialogues, Huy Dao, Lizi Liao Nov 2025

One Planner To Guide Them All! Learning Adaptive Conversational Planners For Goal-Oriented Dialogues, Huy Dao, Lizi Liao

Research Collection School Of Computing and Information Systems

Goal-oriented dialogues, such as recommendation and negotiation, often require balancing multiple, conflicting objectives. Existing methods typically involve training separate models for specific combinations of objectives, leading to computational and scalability issues. In this work, we aim to develop a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining. This raises several challenges in terms of both (1) optimization strategy and (2) knowledge utilization. To address these, we propose a novel learning framework, Preference Adaptive Dialogue Policy Planner (PADPP), for multi-objective goal-oriented dialogues. Specifically, to tackle the former, we introduce a novel policy optimization …

Go to article

Context-Aware Hierarchical Taxonomy Generation For Scientific Papers Via Llm-Guided Multi-Aspect Clustering, Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin Nov 2025

Context-Aware Hierarchical Taxonomy Generation For Scientific Papers Via Llm-Guided Multi-Aspect Clustering, Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin

Research Collection School Of Computing and Information Systems

The rapid growth of scientific literature demands efficient methods to organize and synthesize research findings. Existing taxonomy construction methods, leveraging unsupervised clustering or direct prompting of large language models (LLMs), often lack coherence and granularity. We propose a novel context-aware hierarchical taxonomy generation framework that integrates LLM-guided multi-aspect encoding with dynamic clustering. Our method leverages LLMs to identify key aspects of each paper (e.g., methodology, dataset, evaluation) and generates aspect-specific paper summaries, which are then encoded and clustered along each aspect to form a coherent hierarchy. In addition, we introduce a new evaluation benchmark of 156 expert-crafted taxonomies encompassing 11.6k …

Go to article

Distillcaps: Enhancing Audio-Language Alignment In Captioning Via Retrieval-Augmented Knowledge Distillation, Thinh Pham, Nghiem Diep, Lizi Liao, Binh Nguyen Nov 2025

Distillcaps: Enhancing Audio-Language Alignment In Captioning Via Retrieval-Augmented Knowledge Distillation, Thinh Pham, Nghiem Diep, Lizi Liao, Binh Nguyen

Research Collection School Of Computing and Information Systems

Automated audio captioning (AAC) benefits from incorporatingexternal context to interpret complex sounds, but doing so withretrieval-augmented generation (RAG) at inference is sometimesinfeasible due to data availability or incurs significant latency andcomplexity. We propose DistillCaps, a novel training-time frame-work that leverages RAG to guide knowledge distillation for im-proved audio-language alignment, while lessening the relianceon retrieval during inference. In our framework, a RAG-equippedteacher model retrieves relevant textual information (e.g., simi-lar captions) for each audio clip and uses it for training to gener-ate context-enriched captions. Simultaneously, a student model istrained to imitate this teacher, learning to produce high-qualitycaptions from audio alone. We further …

Go to article

Probabilistic Prototype Calibration Of Vision-Language Models For Generalized Few-Shot Semantic Segmentation, Jie Liu, Jiayi Shen, Pan Zhou, Jan-Jakob Sonke, Stratis Gavves Oct 2025

Probabilistic Prototype Calibration Of Vision-Language Models For Generalized Few-Shot Semantic Segmentation, Jie Liu, Jiayi Shen, Pan Zhou, Jan-Jakob Sonke, Stratis Gavves

Research Collection School Of Computing and Information Systems

Generalized Few-Shot Semantic Segmentation (GFSS) aims to extend a segmentation model to novel classes with only a few annotated examples while maintaining performance on base classes. Recently, pretrained vision-language models (VLMs) such as CLIP have been leveraged in GFSS to improve generalization on novel classes through multi-modal prototypes learning. However, existing prototype-based methods are inherently deterministic, limiting the adaptability of learned prototypes to diverse samples, particularly for novel classes with scarce annotations. To address this, we propose FewCLIP, a probabilistic prototype calibration framework over multi-modal prototypes from the pretrained CLIP, thus providing more adaptive prototype learning for GFSS. Specifically, FewCLIP …

Go to article

Boosting Chart-To-Code Generation In Mllm Via Dual Preference-Guided Refinement, Zhihan Zhang, Yixin Cao, Lizi Liao Oct 2025

Boosting Chart-To-Code Generation In Mllm Via Dual Preference-Guided Refinement, Zhihan Zhang, Yixin Cao, Lizi Liao

Research Collection School Of Computing and Information Systems

Translating chart images into executable plotting scripts-referred to as the chart-to-code generation task-requires Multimodal Large Language Models (MLLMs) to perform fine-grained visual parsing, precise code synthesis, and robust cross-modal reasoning. However, this task is inherently under-constrained: multiple valid code implementations can produce the same visual chart, and evaluation must consider both code correctness and visual fidelity across diverse dimensions. This makes it difficult to learn accurate and generalizable mappings through standard supervised fine-tuning. To address these challenges, we propose a dual preference-guided refinement framework that combines a feedback-driven, dual-modality reward mechanism with iterative preference learning. Our approach introduces a structured …

Go to article

Auxiliary Prompt Tuning Of Vision‑Language Models For Few‑Shot Out‑Of‑Distribution Detection, Wenjun Miao, Guansong Pang, Zihan Wang, Jin Zheng, Xiao Bai Oct 2025

Auxiliary Prompt Tuning Of Vision‑Language Models For Few‑Shot Out‑Of‑Distribution Detection, Wenjun Miao, Guansong Pang, Zihan Wang, Jin Zheng, Xiao Bai

Research Collection School Of Computing and Information Systems

Recent advancements in CLIP-based out-of-distribution (OOD) detection have shown promising results via regularization on prompt tuning, leveraging background features extracted from a few in-distribution (ID) samples as proxies for OOD features.However, these methods suffer from an inherent limitation: a lack of diversity in the extracted OOD features from the few-shot ID data.To address this issue, we propose to leverage external datasets as auxiliary outlier data (i.e., pseudo OOD samples) to extract rich, diverse OOD features, with the features from not only background regions but also foreground object regions, thereby supporting more discriminative prompt tuning for OOD detection. We further introduce …

Go to article

Contrastrepair: Enhancing Conversation-Based Automated Program Repair Via Contrastive Test Case Pairs, Jiaolong Kong, Xiaofei Xie, Mingfei Cheng, Shangqing Liu, Xiaoning Du, Qi Guo Oct 2025

Contrastrepair: Enhancing Conversation-Based Automated Program Repair Via Contrastive Test Case Pairs, Jiaolong Kong, Xiaofei Xie, Mingfei Cheng, Shangqing Liu, Xiaoning Du, Qi Guo

Research Collection School Of Computing and Information Systems

Automated Program Repair (APR) aims to automatically generate patches for rectifying software bugs. Recentstrides in Large Language Models (LLM), such as ChatGPT, have yielded encouraging outcomes in APR,especially within the conversation-driven APR framework. Nevertheless, the efficacy of conversation-drivenAPR is contingent on the quality of the feedback information. In this article, we propose ContrastRepair, anovel conversation-based APR approach that augments conversation-driven APR by providing LLMs withcontrastive test pairs. A test pair consists of a failing test and a passing test, which offer contrastive feedback tothe LLM. Our key insight is to minimize the difference between the generated passing test and the …

Go to article

Polymind: Parallel Visual Diagramming With Large Language Models To Support Prewriting Through Microtasks, Qian Wan, Jiannan Li, Huanchen Wang, Zhicong Lu Oct 2025

Polymind: Parallel Visual Diagramming With Large Language Models To Support Prewriting Through Microtasks, Qian Wan, Jiannan Li, Huanchen Wang, Zhicong Lu

Research Collection School Of Computing and Information Systems

Prewriting is the process of generating and organising ideas before a first draft. It consists of a combination of informal, iterative, and semi-structured strategies such as visual diagramming, which poses a challenge for collaborating with large language models (LLMs) in a turn-taking conversational manner. We present Polymind, a visual diagramming tool that leverages multiple LLM-powered agents to support prewriting. The system features a parallel collaboration workflow in place of the turn-taking conversational interactions. It defines multiple ''microtasks'' to simulate group collaboration scenarios such as collaborative writing and group brainstorming. Instead of repetitively prompting a chatbot for various purposes, Polymind enables …

Go to article

Exploring Parameter-Efficient Fine-Tuning Techniques For Code Generation With Large Language Models, Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, Houari A. Sahraoui Sep 2025

Exploring Parameter-Efficient Fine-Tuning Techniques For Code Generation With Large Language Models, Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, Houari A. Sahraoui

Research Collection School Of Computing and Information Systems

Large language models (LLMs) demonstrate impressive capabilities to generate accurate code snippets given natural language intents in a zero-shot manner, i.e., without the need for specific fine-tuning. While prior studies have highlighted the advantages of fine-tuning LLMs, this process incurs high computational costs, making it impractical in resource-scarce environments, particularly for models with billions of parameters. To address these challenges, previous research explored in-context learning (ICL) and retrieval-augmented generation (RAG) as strategies to guide the LLM generative process with task-specific prompt examples. However, ICL and RAG introduce inconveniences, such as the need for designing contextually relevant prompts and the absence …

Go to article

Next Last