@inproceedings{Li_SEFM_blogs,

title = {Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models},

author = {Hao Li and Cor-Paul Bezemer and Ahmed E. Hassan},

year  = {2025},

date = {2025-04-27},

booktitle = {International Conference on Software Engineering - Software Engineering in Practice (ICSE - SEIP) Track},

abstract = {Foundation models (FMs) such as large language

models (LLMs) have significantly impacted many fields, including

software engineering (SE). The interaction between SE and FMs

has led to the integration of FMs into SE practices (FM4SE)

and the application of SE methodologies to FMs (SE4FM). While

several literature surveys exist on academic contributions to these

trends, we are the first to provide a practitioner’s view. We

analyze 155 FM4SE and 997 SE4FM blog posts from leading

technology companies, leveraging an FM-powered surveying

approach to systematically label and summarize the discussed

activities and tasks. We observed that while code generation is the

most prominent FM4SE task, FMs are leveraged for many other

SE activities such as code understanding, summarization, and

API recommendation. The majority of blog posts on SE4FM are

about model deployment & operation, and system architecture

& orchestration. Although the emphasis is on cloud deployments,

there is a growing interest in compressing FMs and deploying

them on smaller devices such as edge or mobile devices. We

outline eight future research directions inspired by our gained

insights, aiming to bridge the gap between academic findings

and real-world applications. Our study not only enriches the

body of knowledge on practical applications of FM4SE and

SE4FM but also demonstrates the utility of FMs as a powerful

and efficient approach in conducting literature surveys within

technical and grey literature domains. Our dataset, results, code

and used prompts can be found in our online replication package

at https://zenodo.org/records/14563992.},

keywords = {FM4SE, Foundation models, SE4AI, SE4FM, SE4ML},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Taesiri_VideoGameBunny,

title = {VIDEOGAMEBUNNY: Towards vision assistants for video games},

author = {Mohammad Reza Taesiri and Cor-Paul Bezemer },

year  = {2025},

date = {2025-03-01},

booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},

abstract = {Large multimodal models (LMMs) hold substantial

promise across various domains, from personal assistance

in daily tasks to sophisticated applications like medical di-

agnostics. However, their capabilities have limitations in

the video game domain, such as challenges with scene un-

derstanding, hallucinations, and inaccurate descriptions of

video game content, especially in open-source models. This

paper describes the development of VIDEOGAMEBUNNY,

a LLaVA-style model based on Bunny, specifically tailored

for understanding images from video games. We release

intermediate checkpoints, training logs, and an extensive

dataset comprising 185,259 video game images from 413

titles, along with 389,565 image-instruction pairs that in-

clude image captions, question-answer pairs, and a JSON

representation of 16 elements of 136,974 images. Our ex-

periments show that our high quality game-related data

has the potential to make a relatively small model outper-

form the much larger state-of-the-art model LLaVa-1.6-34b

(which has more than 4x the number of parameters). Our

study paves the way for future research in video game un-

derstanding on tasks such as playing, commentary, and

debugging. Code and data are available at: https://videogamebunny.github.io/},

keywords = {Computer games, Foundation models, Game development, Game testing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{TaesiriCVPR2024,

title = {GlitchBench: Can large multimodal models detect video game glitches?},

author = {Mohammad Reza Taesiri and Tianjun Feng and Anh Nguyen and Cor-Paul Bezemer},

year  = {2024},

date = {2024-06-15},

urldate = {2024-03-15},

booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},

abstract = {Large multimodal models (LMMs) have evolved from

large language models (LLMs) to integrate multiple input

modalities, such as visual inputs. This integration augments

the capacity of LLMs for tasks requiring visual comprehen-

sion and reasoning. However, the extent and limitations of

their enhanced abilities are not fully understood, especially

when it comes to real-world tasks. To address this gap, we

introduce GlitchBench, a novel benchmark derived from

video game quality assurance tasks, to test and evaluate the

reasoning capabilities of LMMs. Our benchmark is curated

from a variety of unusual and glitched scenarios from video

games and aims to challenge both the visual and linguis-

tic reasoning powers of LMMs in detecting and interpreting

out-of-the-ordinary events. We evaluate multiple state-of-

the-art LMMs, and we show that GlitchBench presents a

new challenge for these models. Code and data are avail-

able at: https://glitchbench.github.io/},

keywords = {Computer games, Foundation models, Game development, Gameplay videos, LLM},

pubstate = {published},

tppubtype = {inproceedings}

}