arXiv subjects

George K. Thiruvathukal

Publications and source records attributed to George K. Thiruvathukal.

At least 19 recordsLinked to original sources

arXiv2026

On a Separate Note: Robust Score-Informed Note Separation with a Two-Stream TFC-TDF U-Net and Adaptive Set Ownership

Score-informed note separation seeks to extract the performed waveform of all individual notes, often from a polyphonic recording. Existing deep learning systems generally only target instrument-level stems. We present, to our knowledge, the first deep learning approach to score-informed note separation, NoteSep. NoteSep extracts the queried notes by applying an extraction stage model, NoteGrab, once per note. Conditioned on pitch, onset, and offset, NoteGrab separates harmonic and percussive components in two U-Nets linked by bidirectional cross-attention; selective harmonic gating suppresses lower-octave interference while preserving percussive attacks. Finally, a joint separation stage applies Adaptive Set Ownership (ASO) to compare concurrent NoteGrab estimates and reallocate mixture energy. We curate SCNS-Train (25,729 mixtures and 743,920 targets) for training and SCNS-Eval (16 instruments, disjoint scores and libraries) for evaluation. On SCNS-Eval, NoteSep reaches a median SI-SDR of 7.39~dB, compared with 2.49~dB for our strongest baseline. See the demo page at https://benschou.com/notesep.

cs.SD↗

arXiv2026

Object Model Analysis of a Supercomputer with Digital Twin

Operators and developers need a mental model of both the structure and the live behavior of a large supercomputer, but its physical layout, logical organization, and streams of per-node telemetry are difficult to relate to one another, making it hard to trace a metric or event back to a specific hardware component. We present DAT, an interactive three-dimensional digital analytics twin of a compute cluster built in a real-time game engine, Unreal Engine. DAT expands a compact, parametric description of a supercomputer, a reusable Digital Twin Prototype (DTP), into a navigable Digital Twin Instance (DTI) that mirrors its physical containment hierarchy of racks, chassis, blades, and network links, encoding each node's role and health in its appearance, while a lightweight event-driven simulator animates job and hardware activity over a virtual clock. Our current implementation adds a two-path node-selection mechanism, unifying direct 3D pointing with command-shell queries, that opens an in-world visual-analytics panel beside any selected component showing summary statistics and live, time-varying metrics. We describe this architecture, report qualitative behavior from the working prototype, and outline the path toward driving the panels with recorded telemetry and in-situ anomaly detection.

cs.DC↗

arXiv2026

An Empirical Investigation of Pre-Trained Deep Learning Model Reuse in the Scientific Process

Deep learning has achieved recognition for its impact within natural sciences, yet the prohibitive financial and technical cost of training models from scratch inhibit adoption. Following software engineering community guidance, natural scientists are reusing pre-trained deep learning models (PTMs) to amortize these costs. While prior works recommend PTM reuse patterns, we present the first empirical study of PTM reuse patterns in the natural sciences, quantifying the utilization and impact of PTM reuse within the scientific process across 17,718 peer reviewed, open access papers. Our results show that "Biochemistry, Genetics and Molecular Biology" has outpaced other natural scientific fields in PTM reuse, "adaptation" reuse is the most prevalent PTM reuse pattern identified across all natural science fields, and the "testing" stage of the scientific process has been most impacted by PTM integration.

cs.SE↗

arXiv2026

TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation

TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols. Large language models (LLMs) frequently produce TLA+ specifications that fail the TLC model checker for semantic reasons. Across 25 LLMs, the best public baseline is 26.6% syntactic parse and 8.6% semantic model-check. We present TLA-Prover, a 20-billion-parameter model for TLA+ specification synthesis. Training combines supervised fine-tuning (SFT) on verified examples with repair-based group-relative policy optimization (GRPO). In the GRPO stage, the model learns to fix its own rejected specifications. We also train a direct preference optimization (DPO) variant from the same SFT checkpoint as an ablation. TLC provides the reward signal directly, with no learned reward model. Four tiers grade each output: Bronze (parses), Silver (no warnings), Gold (passes TLC), and Diamond. To reach Diamond, the model's correctness property is automatically altered in a small way; TLC must then detect a violation. If TLC still passes, the property was always-true and contributes nothing; the output fails Diamond. TLA-Prover reaches 9/30 (i.e. pass@1 = 30%) at both Gold and Diamond on a held-out 30-problem benchmark. This is roughly 3.5x the 8.6% untuned baseline. The DPO variant reaches 20% at Diamond. Gold and Diamond coincide at every checkpoint; this prevents the trivial-property failure mode.

cs.SE↗

arXiv2026

TLA+-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA Specification Generation

Large language models increasingly write TLA$^{+}$ formal specifications from natural-language descriptions, but progress is hard to measure: existing resources grade by resemblance to a reference or by whether the output parses, neither of which shows correctness. We present TLA$^{+}$-Bench, a dataset and benchmark that grades by execution. Every gold specification ships a configuration the TLA$^{+}$ model checker runs over the full reachable state space, deciding exactly whether the specification holds the properties that configuration names. The dataset holds 403 model-checked gold and 897 parse-only silver specifications from 13 public repositories, subsumes prior TLA$^{+}$ generation data, and carries four model-written descriptions in two styles from two providers, with difficulty and category labels. Our main finding is about measurement itself: an exact oracle gives not one correctness number but a range. Varying only the grading choices earlier benchmarks leave unstated, on one fixed set of model outputs, the correct rate moves sixfold, from 10.0\% to 1.7\%; adding the interface-supply choice, where the model is told the configuration's names, widens the range to elevenfold, from 18.7\% to 1.7\%. We call this range the correctness envelope and measure each of its bounds. The findings inside it are stable. Every model writes valid TLA$^{+}$ far more often than correct TLA$^{+}$: the strongest is correct 16\% of the time by default and 26\% when given the interface names, open models at most 1\%, and correctness falls sharply with difficulty.

cs.SE↗

arXiv2026

Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation

TLA+ has supported industrial verification at companies such as Amazon and Microsoft, yet writing correct TLA+ specifications from natural language still requires time and expertise, which limits adoption. LLMs show promise, but no prior study measures whether they produce semantically correct TLA+ specifications from natural language. This paper presents the first systematic evaluation of LLM-based TLA+ specification synthesis from natural language. Our study evaluates 30 LLMs across eight families on a curated dataset of 205 TLA+ specifications: 25 open-weight models across four prompting strategies (2,600 runs) and 5 proprietary models under few-shot prompting (130 runs), all validated by the SANY parser and TLC model checker. LLMs achieve up to 26.6% syntactic correctness but only 8.6% semantic correctness, with successes exclusive to progressive prompting. Results show that model size does not predict quality, e.g., DeepSeek r1:8b outperforms its 70B variant across all strategies, which suggests the importance of reasoning alignment for formal languages. Code-specialized models consistently underperform due to negative transfer from mainstream language training. We identify five recurring hallucination categories, all traceable to specific training data biases. These results suggest that current LLMs do not generate reliable TLA+ specifications without expert oversight. We release the evaluation framework, code, and dataset to support reproducibility and future research.

cs.AI↗

arXiv2026

SysLLMatic: Large Language Models are Software System Optimizers

Automatic software system optimization can improve software speed, reduce operating costs, and save energy. Traditional approaches to optimization rely on manual tuning and compiler heuristics, limiting their ability to generalize across diverse codebases and system contexts. Recent methods using Large Language Models (LLMs) introduce automation on simple programs, but they do not scale effectively to the complexity and size of real-world software systems. We present SysLLMatic, a system that integrates LLMs with performance diagnostics and a curated catalog of 43 optimization patterns to automatically optimize software systems. By leveraging profiling to identify performance hotspots, our approach enables LLMs to optimize real-world software beyond isolated code snippets. We evaluate it on three benchmark suites: HumanEval_CPP (competitive programming in C++), SciMark2 (scientific kernels in Java), and DaCapo (large-scale software systems in Java). Results show that SysLLMatic can improve software system performance, including latency, throughput, energy efficiency, memory usage, and CPU utilization. It consistently outperforms state-of-the-art LLM baselines on microbenchmarks. On large-scale application codes, to which prior LLM approaches have not scaled, it surpasses compiler optimizations, achieving average relative improvements of 1.54x in latency (vs. 1.01x for the compiler) and 1.24x in energy (vs. 1.08x for the compiler). Our findings demonstrate that LLMs, guided by performance knowledge through the optimization pattern catalog and appropriate performance diagnostics, can serve as viable software system optimizers. We further identify limitations of our approach and the challenges involved in handling complex applications. This work provides a foundation for generating optimized code across various languages, benchmarks, and program sizes in a principled manner.

cs.SE↗

arXiv2026

Now's the Time: Computer Science Must Evolve to Emphasize Software and Systems Engineering with Artificial Intelligence (AI)

Computer science (CS) education needs to evolve to support software and artificial intelligence (AI) systems engineering, and it needs to happen now -- precisely because the core intellectual contributions of CS have never been more important. We argue that traditional curricula, built around programming, data structures, and algorithms as ends in themselves, must be reframed so that these topics become foundational building blocks within a systems- and engineering-centered education. Graduates should be prepared not to compete with AI on routine coding tasks, but to design, orchestrate, verify, and own complex AI-enabled systems operating under real-world constraints. More importantly, computer science education should be geared toward preparing students for future disruptions. The broad history of computing is marked by one disruptive technology after another, requiring us to rise to the moment instead of merely acquiescing to it.

cs.SE↗

arXiv2026

HeyFriend Helper: A Conversational AI Web-App for Resource Access Among Low-Income Chicago Residents

Low-income individuals can face multiple challenges in their ability to seek employment. Barriers to employment often include limited access to digital literacy resources, training, interview preparation and resume feedback. Prior work has largely focused on targeted social service or healthcare applications that address needs individually, with little emphasis on conversational AI-driven systems that integrate multiple localized digital resources to provide comprehensive support. This work presents HeyFriend Helper, a web-based platform designed to support low-income residents in Chicago through an interactive conversational assistant that provides personalized support and guidance. HeyFriend Helper integrates multiple tools, including resume building and feedback, interview practice, mindfulness and well-being resources, employment trend and career outcome information, language learning support, and location-based access to community services. This work represents an interdisciplinary collaboration between social work, computer science, and engineering that addresses the multifaceted needs of low-income individuals. The findings demonstrate the importance of career-readiness tools and conversational user interface (CUIs) in providing holistic support.

cs.HC↗

arXiv2026

Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization

Large language models and AI agents have recently shown promise in automating software performance optimization, but existing approaches predominantly rely on local, syntax-driven code transformations. This limits their ability to reason about program behavior and capture whole system performance interactions. As modern software increasingly comprises interacting components - such as microservices, databases, and shared infrastructure - effective code optimization requires reasoning about program structure and system architecture beyond individual functions or files. This paper explores the feasibility of whole system optimization for microservices. We introduce a multi-agent framework that integrates control-flow and data-flow representations with architectural and cross-component dependency signals to support system-level performance reasoning. The proposed system is decomposed into coordinated agent roles - summarization, analysis, optimization, and verification - that collaboratively identify cross-cutting bottlenecks and construct multi-step optimization strategies spanning the software stack. We present a proof-of-concept on a microservice-based system that illustrates the effectiveness of our proposed framework, achieving a 36.58% improvement in throughput and a 27.81% reduction in average response time.

cs.SE↗

arXiv2026

LadderSym: A Multimodal Interleaved Transformer for Music Practice Error Detection

Music learners can greatly benefit from tools that accurately detect errors in their practice. Existing approaches typically compare audio recordings to music scores using heuristics or learnable models. This paper introduces LadderSym, a novel Transformer-based method for music error detection. LadderSym is guided by two key observations about the state-of-the-art approaches: (1) late fusion limits inter-stream alignment and cross-modality comparison capability; and (2) reliance on score audio introduces ambiguity in the frequency spectrum, degrading performance in music with concurrent notes. To address these limitations, LadderSym introduces (1) a two-stream encoder with inter-stream alignment modules to improve audio comparison capabilities and error detection F1 scores, and (2) a multimodal strategy that leverages both audio and symbolic scores by incorporating symbolic representations as decoder prompts, reducing ambiguity and improving F1 scores. We evaluate our method on the MAESTRO-E and CocoChorales-E datasets by measuring the F1 score for each note category. Compared to the previous state of the art, LadderSym more than doubles F1 for missed notes on MAESTRO-E (26.8% -> 56.3%) and improves extra note detection by 14.4 points (72.0% -> 86.4%). Similar gains are observed on CocoChorales-E. Furthermore, we also evaluate our models on real data we curated. This work introduces insights about comparison models that could inform sequence evaluation tasks for reinforcement learning, human skill assessment, and model evaluation. Code: https://github.com/ben2002chou/LadderSYM

cs.SD↗

arXiv2026

AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents

LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software package registries (e.g., npm) and model hubs (e.g., Hugging Face). Existing efforts typically address naming, distribution, or protocol descriptors, but stop short of providing a registry layer that makes agents discoverable, comparable, and governable under automated reuse. We present AgentHub, a registry layer and accompanying research agenda for agent sharing that targets discovery and workflow integration, trust and security, openness and governance, ecosystem interoperability, lifecycle transparency, and capability clarity with evidence. We describe a reference prototype that implements a canonical manifest with publish-time validation, version-bound evidence records linked to auditable artifacts, and an append-only lifecycle event log whose states are respected by default in search and resolution. We also provide initial discovery results using an LLM-as-judge recommendation pipeline, showing how structured contracts and evidence improve intent-accurate retrieval beyond keyword-driven discovery. AgentHub aims to provide a common substrate for building reliable, reusable agent ecosystems.

cs.SE↗

arXiv2026

Operationalizing Research Software for Supply Chain Security

Empirical studies of research software are hard to compare because the literature operationalizes ``research software'' inconsistently. Motivated by the research software supply chain (RSSC) and its security risks, we introduce an RSSC-oriented taxonomy that makes scope and operational boundaries explicit for empirical research software security studies. We conduct a targeted scoping review of recent repository mining and dataset construction studies, extracting each work's definition, inclusion criteria, unit of analysis, and identification heuristics. We synthesize these into a harmonized taxonomy and a mapping that translates prior approaches into shared taxonomy dimensions. We operationalize the taxonomy on a large community-curated corpus from the Research Software Encyclopedia (RSE), producing an annotated dataset, a labeling codebook, and a reproducible labeling pipeline. Finally, we apply OpenSSF Scorecard as a preliminary security analysis to show how repository-centric security signals differ across taxonomy-defined clusters and why taxonomy-aware stratification is necessary for interpreting RSSC security measurements.

cs.SE↗

arXiv2026

Process-based Indicators of Vulnerability Re-Introducing Code Changes: An Exploratory Case Study

Software vulnerabilities often persist or re-emerge even after being fixed, revealing the complex interplay between code evolution and socio-technical factors. While source code metrics provide useful indicators of vulnerabilities, software engineering process metrics can uncover patterns that lead to their introduction. Yet few studies have explored whether process metrics can reveal risky development activities over time -- insights that are essential for anticipating and mitigating software vulnerabilities. This work highlights the critical role of process metrics along with code changes in understanding and mitigating vulnerability reintroduction. We move beyond file-level prediction and instead analyze security fixes at the commit level, focusing not only on whether a single fix introduces a vulnerability but also on the longer sequences of changes through which vulnerabilities evolve and re-emerge. Our approach emphasizes that reintroduction is rarely the result of one isolated action, but emerges from cumulative development activities and socio-technical conditions. To support this analysis, we conducted a case study on the ImageMagick project by correlating longitudinal process metrics such as bus factor, issue density, and issue spoilage with vulnerability reintroduction activities, encompassing 76 instances of reintroduced vulnerabilities. Our findings show that reintroductions often align with increased issue spoilage and fluctuating issue density, reflecting short-term inefficiencies in issue management and team responsiveness. These observations provide a foundation for broader studies that combine process and code metrics to predict risky fixes and strengthen software security.

cs.SE↗

arXiv2025

Inference-Time Alignment of Diffusion Models via Evolutionary Algorithms

Diffusion models are state-of-the-art generative models, yet their samples often fail to satisfy application objectives such as safety constraints or domain-specific validity. Existing techniques for alignment require gradients, internal model access, or large computational budgets resulting in high compute demands, or lack of support for certain objectives. In response, we introduce an inference-time alignment framework based on evolutionary algorithms. We treat diffusion models as black boxes and search their latent space to maximize alignment objectives. Given equal or less running time, our method achieves 3-35% higher ImageReward scores than gradient-free and gradient-based methods. On the Open Image Preferences dataset, our method achieves competitive results across four popular alignment objectives. In terms of computational efficiency, we require 55% to 76% less GPU memory and are 72% to 80% faster than gradient-based methods.

cs.LG↗

arXiv2025

AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens

Modern transformer architectures achieve remarkable performance across tasks and domains but remain rigid in how they allocate computation at inference time. Real-world deployment often requires models to adapt to diverse hardware and latency constraints, yet most approaches to dynamic computation focus on a single axis -- such as reducing the number of tokens. We present a novel capability: AdaPerceiver, the first transformer architecture with unified adaptivity across depth, width, and tokens within a single model. We propose an architecture that supports adaptivity along these axes. We couple this with an efficient joint training regime that ensures the model maintains performance across its various configurations. We evaluate AdaPerceiver on image classification, semantic segmentation, and depth estimation tasks. On image classification, AdaPerceiver expands the accuracy-throughput Pareto front. It achieves 85.4% accuracy while yielding 36% higher throughput than FlexiViT-L. On dense prediction, AdaPerceiver matches ViT-H/14 while having $\sim$26x fewer encoder FLOPs (floating-point operations) on semantic segmentation and depth estimation. Finally, we show how AdaPerceiver equipped with a policy can maintain ImageNet1K accuracy ($\pm0.1$ percentage points) while reducing FLOPs by $24-33$%.

cs.CV↗

arXiv2025

"I see models being a whole other thing": An Empirical Study of Pre-Trained Model Naming Conventions and A Tool for Enhancing Naming Consistency

As innovation in deep learning continues, many engineers are incorporating Pre-Trained Models (PTMs) as components in computer systems. Some PTMs are foundation models, and others are fine-tuned variations adapted to different needs. When these PTMs are named well, it facilitates model discovery and reuse. However, prior research has shown that model names are not always well chosen and can sometimes be inaccurate and misleading. The naming practices for PTM packages have not been systematically studied, which hampers engineers' ability to efficiently search for and reliably reuse these models. In this paper, we conduct the first empirical investigation of PTM naming practices in the Hugging Face PTM registry. We begin by reporting on a survey of 108 Hugging Face users, highlighting differences from traditional software package naming and presenting findings on PTM naming practices. The survey results indicate a mismatch between engineers' preferences and current practices in PTM naming. We then introduce DARA, the first automated DNN ARchitecture Assessment technique designed to detect PTM naming inconsistencies. Our results demonstrate that architectural information alone is sufficient to detect these inconsistencies, achieving an accuracy of 94% in identifying model types and promising performance (over 70%) in other architectural metadata as well. We also highlight potential use cases for automated naming tools, such as model validation, PTM metadata generation and verification, and plagiarism detection. Our study provides a foundation for automating naming inconsistency detection. Finally, we envision future work focusing on automated tools for standardizing package naming, improving model selection and reuse, and strengthening the security of the PTM supply chain.

cs.SE↗

arXiv2025

2024 NSF CSSI-Cybertraining-SCIPE PI Meeting August 12 to 13, 2024, Charlotte, NC

The second annual NSF, OAC CSSI, CyberTraining and related programs PI meeting was held August 12 to 13 in Charlotte, NC, with participation from PIs or representatives of all major awards. Keynotes, panels, breakouts, and poster sessions allowed PIs to engage with each other, NSF staff, and invited experts. The 286 attendees represented 292 awards across CSSI, CyberTraining, OAC Core, CIP, SCIPE CDSE, and related programs, and presented over 250 posters. This report documents the meetings structure, findings, and recommendations, offering a snapshot of current community perspectives on cyberinfrastructure. A key takeaway is a vibrant, engaged community advancing science through CI. AI-driven research modalities complement established HPC and data centric tools. Workforce development efforts align well with the CSSI community.

cs.ET↗