Related papers: The Vibe-Check Protocol: Quantifying Cognitive Off…
Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing…
Novice programmers are increasingly relying on Large Language Models (LLMs) to generate code for learning programming concepts. However, this interaction can lead to superficial engagement, giving learners an illusion of learning and…
Vision-Language Pretraining (VLP) has shown impressive results on diverse downstream tasks by offline training on large-scale datasets. Regarding the growing nature of real-world data, such an offline training paradigm on ever-expanding…
The integration of Large Language Models (LLMs), such as ChatGPT and GitHub Copilot, into professional workflows is increasingly reshaping software engineering practices. These tools have lowered the cost of code generation, explanation,…
Vision-Language Pretraining (VLP) models have recently successfully facilitated many cross-modal downstream tasks. Most existing works evaluated their systems by comparing the fine-tuned downstream task performance. However, only average…
With the recent rapid increase in digitization across all major industries, acquiring programming skills has increased the demand for introductory programming courses. This has further resulted in universities integrating programming…
Code generation has emerged as one of AI's highest-impact use cases, yet existing benchmarks measure isolated tasks rather than the complete "zero-to-one" process of building a working application from scratch. We introduce Vibe Code Bench,…
Consistent high-quality nursing care is essential for patient safety, yet current nursing education depends on subjective, time-intensive instructor feedback in training future nurses, which limits scalability and efficiency in their…
Large language models (LLMs) have shown promising results for software engineering applications, but still struggle with code reasoning tasks such as vulnerability detection (VD). We introduce ConceptCoder, a fine-tuning method that…
Behavioral analysis of tutoring dialogues is essential for understanding student learning, yet manual coding remains a bottleneck. We present a methodology where LLM coding agents autonomously improve the prompts used by LLM classifiers to…
We argue that when it comes to producing secure code with AI, the prevailing "fighting fire with fire" approach -- using probabilistic AI-based checkers or attackers to secure probabilistically generated code -- fails to address the long…
Software development is undergoing a fundamental transformation as vibe coding becomes widespread, with large portions of contemporary codebases now being generated by Artificial Intelligence (AI). The disconnect between rapid adoption and…
Code review is a socio-technical practice, yet how software engineers engage in Large Language Model (LLM)-assisted code reviews compared to human peer-led reviews is less understood. We report a two-phase qualitative study with 20 software…
Large pre-trained vision-language models (VLMs) offer a promising approach to leveraging human language for enhancing downstream tasks. However, VLMs such as CLIP face significant limitation: its performance is highly sensitive to prompt…
The rise of Large Language Models (LLMs) in software engineering, particularly in code generation, has garnered significant attention. However, assessing the quality of AI-generated code remains a challenge due to the inherent complexity of…
This Innovative Practice full paper explores how Large Language Models (LLMs) can enhance the teaching of code refactoring in software engineering courses through real-time, context-aware feedback. Refactoring improves code quality but is…
As large language models (LLMs) continue to advance in programming tasks, LLM-driven coding systems have evolved from one-shot code generation into complex systems capable of iterative improvement during inference. However, existing code…
Software developers use metrics to evaluate code quality and productivity, but these practices are still rare in programming education. This project bridges the gap by collecting real-time learning analytics from individual student and…
When MLLMs fail at Science, Technology, Engineering, and Mathematics (STEM) visual reasoning, a fundamental question arises: is it due to perceptual deficiencies or reasoning limitations? Through systematic scaling analysis that…
Recent efforts to accelerate inference in Multimodal Large Language Models (MLLMs) have largely focused on visual token compression. The effectiveness of these methods is commonly evaluated by measuring the accuracy drop on existing MLLM…