Abstract

The communication of scientific knowledge has become increasingly multimodal, spanning text, visuals, and speech through materials such as research papers, slides, and recorded presentations. These different representations collectively convey a study's reasoning, results, and insights, offering complementary perspectives that enrich understanding. However, despite their shared purpose, such materials are rarely connected in a structured way. The absence of explicit links across formats makes it difficult to trace how concepts, visuals, and explanations correspond, limiting unified exploration and analysis of research content.
To address this gap, we introduce the Multimodal Conference Dataset (MCD), the first benchmark that integrates research papers, presentation videos, explanatory videos, and slides from the same works. We evaluate a range of embedding-based and vision-language models to assess their ability to discover fine-grained cross-format correspondences, establishing the first systematic benchmark for this task. Our results show that vision-language models are robust but struggle with fine-grained alignment, while embedding-based models capture text-visual correspondences well but equations and symbolic content form distinct clusters in the embedding space. These findings highlight both the strengths and limitations of current approaches and point to key directions for future research in multimodal scientific understanding. To ensure reproducibility, we release the resources for MCD at https://github.com/meghamariamkm2002/MCD

Abstract

Architecture Knowledge Management (AKM) is crucial for maintaining current and comprehensive software Architecture Knowledge (AK) in a software project. However AKM is often a laborious process and is not adopted by developers and architects. While LLMs present an opportunity for automation, a naive, single-prompt approach is often ineffective, constrained by context limits and an inability to grasp the distributed nature of architectural knowledge. To address these limitations, we propose an Agentic approach for AKM, AgenticAKM, where the complex problem of architecture recovery and documentation is decomposed into manageable sub-tasks. Specialized agents for architecture Extraction, Retrieval, Generation, and Validation collaborate in a structured workflow to generate AK. To validate we made an initial instantiation of our approach to generate Architecture Decision Records (ADRs) from code repositories. We validated our approach through a user study with 29 repositories. The results demonstrate that our agentic approach generates better ADRs, and is a promising and practical approach for automating AKM.

Abstract

Context. The rise of Large Language Models (LLMs) has led to their widespread adoption in development pipelines.
Goal. We empirically assess the energy efficiency of Python code generated by LLMs against human-written code and code developed by a Green software expert.
Method. We test 363 solutions to 9 coding problems from the EvoEval benchmark using 6 widespread LLMs with 4 prompting techniques, and comparing them to human-developed solutions. Energy consumption is measured on three different hardware platforms: a server, a PC, and a Raspberry Pi for a total of ≈881h (36.7 days).
Results. Human solutions are 16% more energy-efficient on the server and 3% on the Raspberry Pi, while LLMs outperform human developers by 25% on the PC. Prompting does not consistently lead to energy savings, where the most energy-efficient prompts vary by hardware platform. The code developed by a Green software expert is consistently more energy-efficient by at least 17% to 30% against all LLMs on all hardware platforms.
Conclusions. Even though LLMs exhibit relatively good code generation capabilities, no LLM-generated code was more energy-efficient than that of an experienced Green software developer, suggesting that as of today there is still a great need of human expertise for developing energy-efficient Python code.

Abstract

Large Language Models (LLMs) are increasingly used in software engineering, yet their role in architectural refactoring, particularly in decomposing monolithic systems into microservices, remains largely unexplored, even though such decomposition, when necessary, is difficult and error-prone, especially when identifying meaningful service boundaries.
This exploratory study investigates how LLMs can support architects through a multi-step decomposition process that applies seven summarisation strategies and four LLMs to generate architectural views and candidate decompositions. We assess these decompositions using six established metrics across four open-source systems that provide both monolithic and microservice versions, enabling comparison with reference architectures.
Results show that LLM-based decompositions outperform traditional techniques on Cyclic Independence (+22.7), approaching reference architectures and indicating better technical dependency management. Traditional automated approaches remain stronger at recovering the ground-truth structure (MoJoFM +24.1), team alignment (TC +11.0), and domain-oriented boundaries (DI +10.7). No significant differences appear for Code Modularity or Business Context Purity, suggesting that LLMs produce clean decompositions with few cyclic dependencies but still struggle to reproduce the exact target decomposition.

Abstract

This work deals with the fundamental problem of characterizing which multiparty distributions can be securely sampled with information-theoretic security against passive corruption, when there is no setup or honest-majority. We focus on the case of 4-party distributions with boolean outputs for each party. We show that such a distribution is securely samplable if and only if every 2-party distribution derived from it by partitioning the parties into two sets is securely samplable. This extends a similar characterization previously known for 3-party distributions.

Abstract

As quick commerce (Q-Commerce) platforms in India redefine urban consumption, the use of deceptive design dark patterns to inflate order values has become a systemic concern. This paper investigates the 'Awareness-Action Gap' among Indian university students, a demographic characterized by high digital fluency yet significant financial constraints. Using a qualitative approach with 16 participants, we explore how temporal pressures and convenience-driven architectures override price sensitivity. Our findings reveal that while students recognize manipulative UI tactics, they frequently succumb to them due to induced cognitive load and the normalization of deceptive marketing as a 'price of capitalism'. We conclude by suggesting value-sensitive design alternatives to align commercial incentives with user autonomy in the Global South.

Abstract

Voluntary movement emerges from coordinated transitions between distributed neural networks operating at sub-second time scales. EEG microstate analysis provides a powerful framework to capture these rapid, large-scale brain dynamics. In this study, the effects of three motor primitives (finger tapping, tip-pinch, and wrist flexion-extension) on microstate temporal parameters were investigated across preparatory, execution, and post-movement recovery phases. EEG data were analyzed from 29 healthy young adults performing these tasks with both hands, alongside an eyes-closed resting condition. Continuous EEG recordings were segmented into three temporal states: pre-event (preparatory), event (motor execution), and post-event (post-movement recovery. Resting-state microstate maps demonstrated significant spatial overlap with established canonical templates, validating their physiological relevance. MS-C (associated with the saliency network) showed a significant increase in duration across all tasks during motor execution and recovery, suggesting sustained network stabilization and subsequent post-movement resetting. Task and hand-specific modulations were observed in MS-A and MS-B, indicating different recruitment of sensorimotor and visual networks. Movement laterality analysis revealed increased post-event coverage of MS-C after right-hand finger tapping. Our analysis presents a normative spatiotemporal baseline for motor primitives, providing a valuable benchmark to evaluate pathological deviations in post-stroke populations.

Abstract

Stroke can often result in Dysarthria, a neuromotor speech impairment that diminishes intelligibility and adversely affects communication and quality of life. Manual evaluation of intelligibility by speech therapists is subjective and labor-intensive, complicating detection of subtle articulatory differences. In this preliminary study, we propose an unsupervised, objective framework for evaluating speech intelligibility in Telugu speaking post-stroke patients. Speech data were collected from ten participants using a phonemically structured set of 38 Telugu words designed to involve different articulatory muscles. Intelligibility was measured as the Dynamic Time Warping (DTW) distance between patient and reference embeddings derived from pretrained Wav2Vec2-Large-XLSR-53-Telugu model.

Our results demonstrate that the proposed PI score reliably distinguishes intelligible and unintelligible speech samples, achieving an F1 score of 94% with over 90% classification accuracy against human perceptual intelligibility ratings. While traditional assessments methods yield a single cumulative score per individual, our methodological framework and stimulus design enables word-level analysis that identifies phoneme-specific misarticulations, thereby supporting targeted therapy for post stroke patients. Collectively, our findings present an automated intelligibility evaluation technique by incorporating unsupervised speech representation learning for post-stroke speech assessment.

Abstract

Accurate transistor sizing remains a major challenge
in analog integrated circuit design due to the highly nonlinear and
many-to-one relationship between device dimensions and circuit
performance metrics. Conventional design flows rely on repeated
SPICE simulations and manual tuning, resulting in significant
computational cost and long design cycles. A feasibility-aware
inverse machine framework is proposed for specification-driven
analog circuit design. The framework directly determines tran
sistor dimensions from target performance specifications such
as gain, bandwidth, phase margin, and power. A multi-output
surrogate model enables rapid performance prediction, while a
genetic-algorithm-based inverse optimizer searches for feasible
sizing solutions. The framework introduces specification-space
feasibility filtering prior to optimization to prevent convergence
toward unattainable targets. Experimental results across mul
tiple analog circuit architectures demonstrate that the proposed
method produces SPICE-validated transistor sizing solutions with
specification errors below 5%.

Abstract

Context: Architecture views are essential for soft-
ware architecture documentation, yet their manual creation is labor-intensive and often leads to outdated artifacts. As systems grow in complexity, the automated generation of views from source code becomes increasingly valuable.
Goal: We empirically evaluate the ability of LLMs and agentic approaches to generate architecture views from source code.
Method: We analyze 340 open-source repositories across 13 experimental configurations using 3 LLMs with 3 prompting techniques and 2 agentic approaches, yielding 4,137 generated views. We evaluate the generated views by comparing them with the ground-truth using a combination of automated metrics complemented by human evaluations.
Results: Prompting strategies offer marginal improvements. Few-shot prompting reduces clarity failures by 9.2% compared to zero-shot baselines. The custom agentic approach consistently outperforms the general purpose agent, achieving the best clarity
(22.6% failure rate) and level of detail success (50%).
Conclusions: LLM and agentic approaches demonstrate capabilities in generating syntactically valid architecture views. However, they consistently exhibit granularity mismatches, operating at the code level rather than architectural abstractions. This suggests
that there is still a need for human expertise, positioning LLMs and agents as assistive tools rather than autonomous architects.