Tootfinder

This https://arxiv.org/abs/2405.03536 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

Extensional and Non-extensional Functions as Processes
Following Milner's seminal paper, the representation of functions as processes has received considerable attention. For pure $λ$-calculus, the process representations yield (at best) non-extensional $λ$-theories (i.e., $β$ rule holds, whereas $η$ does not). In the paper, we study how to obtain extensional representations, and how to move between extensional and non-extensional representations. Using Internal $π$, $\mathrm{I}π$ (a subset of the $π$-calculus in which all outputs are boun…

CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment
Papa S\'ega Wade, Mihai Andries, Ioannis Kanellos, Thierry Moudenc
https://arxiv.org/abs/2506.20243

CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment
Automatic fluency assessment (AFA) remains challenging, particularly in capturing speech rhythm, pauses, and disfluencies in non-native speakers. We introduce a chunk-based approach integrating self-supervised learning (SSL) models (Wav2Vec2, HuBERT, and WavLM) selected for their complementary strengths in phonetic, prosodic, and noisy speech modeling, with a hierarchical CNN-BiLSTM framework. Speech is segmented into breath-group chunks using Silero voice activity detection (Silero-VAD), enabl…

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning
Ankan Deria, Adinath Madhavrao Dukre, Feilong Tang, Sara Atito, Sudipta Roy, Muhammad Awais, Muhammad Haris Khan, Imran Razzak
https://arxiv.org/abs/2506.15649

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning
Despite significant advances in inference-time search for vision-language models (VLMs), existing approaches remain both computationally expensive and prone to unpenalized, low-confidence generations which often lead to persistent hallucinations. We introduce \textbf{Value-guided Inference with Margin-based Reward (ViMaR)}, a two-stage inference framework that improves both efficiency and output fidelity by combining a temporal-difference value model with a margin-aware reward adjustment. In th…

Navigating the growing field of research on AI for software testing -- the taxonomy for AI-augmented software testing and an ontology-driven literature survey
Ina K. Schieferdecker
https://arxiv.org/abs/2506.14640

Navigating the growing field of research on AI for software testing -- the taxonomy for AI-augmented software testing and an ontology-driven literature survey
In industry, software testing is the primary method to verify and validate the functionality, performance, security, usability, and so on, of software-based systems. Test automation has gained increasing attention in industry over the last decade, following decades of intense research into test automation and model-based testing. However, designing, developing, maintaining and evolving test automation is a considerable effort. Meanwhile, AI's breakthroughs in many engineering fields are opening…

It's #NoKings day!
🚫👑🚫👑🚫👑🚫
Be loud. Be heard. Be safe.
⸻
EFF Protest Guide:
•⁠📱⁠https://mastodon.social/@eff/114678037068775207
Know Your Rights:
•⁠🚨⁠…

ImpReSS: Implicit Recommender System for Support Conversations
Omri Haller, Yair Meidan, Dudu Mimran, Yuval Elovici, Asaf Shabtai
https://arxiv.org/abs/2506.14231

ImpReSS: Implicit Recommender System for Support Conversations
Following recent advancements in large language models (LLMs), LLM-based chatbots have transformed customer support by automating interactions and providing consistent, scalable service. While LLM-based conversational recommender systems (CRSs) have attracted attention for their ability to enhance the quality of recommendations, limited research has addressed the implicit integration of recommendations within customer support interactions. In this work, we introduce ImpReSS, an implicit recomme…

Automatic computation of the glycemic index: data driven analysis of the glucose standard
Fabio Credali, Maria Teresa Venuti, Daniele Boffi, Paola Rossi
https://arxiv.org/abs/2506.15471

Automatic computation of the glycemic index: data driven analysis of the glucose standard
The Glycemic Index (GI) is a tool for classifying carbohydrates based on their impact on postprandial glycemia, useful for diabetes prevention and management. This study applies a mathematical model for a data driven simulation of the glycemic response following glucose ingestion. The analysis reveals a direct correlation between glucose response profiles and parameters describing glucose absorption, enabling the classification of subjects into three groups based on the timing of their glycemic…

The fediverse is often full of drama with admins falling out with each other and defederations, and threats and tears.
Now, with the public spat between the Twitter admin and the TruthSocial admin, the rest of the world gets to enjoy a similar spectacle!
They can't defederate of course, because Twitter never became open enough and TruthSocial was already defederated by everyone as soon as it existed.
Only on Fedi can you get the full experience of a public spat and defederation, because only on Fedi can the admins really at-mention and and directly reply and take the final dramatic action of a flouce-defederation.
Trump fans who are Twitter users can't port their followers over to TruthSocial, and Turther Musk fans can't just migrate their account to Twitter.
They're stuck.
So you see Fedi really is the best when it comes to massive public spats between admins and this current admin-drama is only getting more attention because it's between two of the worst people in the world.
#fediverse #interInstanceDrama #adminFight

Admitted symmetries of Backward Stochastic Differential Equations
Anas Ouknine, Paul Lescot
https://arxiv.org/abs/2506.10650 https://…

Admitted symmetries of Backward Stochastic Differential Equations
In this article, we introduce the concept of admitted Lie group of transformations for both backward stochastic differential equations (BSDEs) and forward backward stochastic differential equations (FBSDEs), following the approach of Meleshko et al. An application to BSDE is presented.

DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation
Jingyu Xiao, Ming Wang, Man Ho Lam, Yuxuan Wan, Junliang Liu, Yintong Huo, Michael R. Lyu
https://arxiv.org/abs/2506.06251

DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in automated front-end engineering, e.g., generating UI code from visual designs. However, existing front-end UI code generation benchmarks have the following limitations: (1) While framework-based development becomes predominant in modern front-end programming, current benchmarks fail to incorporate mainstream development frameworks. (2) Existing evaluations focus solely on the UI code generation task, whereas p…