AI News Archive: June 30, 2026 — Part 17
Sourced from 500+ daily AI sources, scored by relevance.
- Cliptych
Highlight a quote on any page → get a LinkedIn carousel
- SessionRoll
SessionRoll is a TTRPG campaign generator and GM workspace
- Forkit Dev AI Passport
AI evidence layer for models and agents
- AI Music Detection API by Modulate
Detect AI-generated music before it reaches monetization.
- ForecastAgentSearch: Towards a Multi-Expert Agent Search System for Geopolitical Event Forecasting
Geopolitical event forecasting is a challenging task, as it requires understanding complex regional contexts, dynamic event signals, and uncertain future outcomes. Recent advances in large language model agents provide new opportunities for building forecasting systems that can reason with diverse s...
- A Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agents
Fault recovery in process plants still relies heavily on plant operators, especially when faults fall outside predefined supervisory logic. Operators interpret alarms, procedures, P\&IDs, interlocks, and process trends, then decide how to move the plant to a safe operating mode without triggering a ...
- Holonic Active Distillation for Scalable Multi-Agent Learning in Multi-Sensor Systems
The rapid expansion of sensor-based networks introduces major challenges in scalability, adaptability, and knowledge transfer, especially in open environments where new subsystems can dynamically join or leave. In this work, we propose a Holonic Active Distillation architecture within a Holonic Mult...
- DataEvolver: Self-Evolving Multi-Agent Data Construction for Text-Rich Image Generation
Text-rich image generation is one of the most challenging settings in image generation, since models must simultaneously produce visually realistic images and render legible, semantically aligned, and layout-consistent text. Existing data pipelines usually follow a static crawl-filter-freeze paradig...
- Investigating LLM-Powered Dissenting Minority Support in Power-Imbalanced Group Decision-Making: Counterargument and Mediation as Intervention Strategies
Minority viewpoints are often suppressed in power-imbalanced group decision-making due to social pressure to comply with the majority. To address this problem, we developed an LLM-powered dissenting minority support system that aimed to foster attention to minority views through either AI-generated ...
- AA: A Multi-view Multimodal Dataset for Screen-based Gaze Estimation
We present AA, a multi-view multimodal dataset for screen-based gaze estimation. The dataset captures synchronized facial observations from eight fixed screen-mounted cameras and two additional side-view cameras, paired with precise screen-space gaze targets collected under controlled fixation condi...
- Building a Multimodal Dataset of Academic Paper for Keyword Extraction
Up to this point, keyword extraction task typically relies solely on textual data. Neglecting visual details and audio features from image and audio modalities leads to deficiencies in information richness and overlooks potential correlations, thereby constraining the model's ability to learn repres...
- From Idea to Prototype in an Afternoon: Scaffolded, AI-Assisted Rapid VA Prototyping
Testing a new visual-analytics idea usually takes months: one needs to find a realistic data set, clean it, and implement an interactive prototype. We describe a case where a workflow language and an AI assistant reduced this effort to one afternoon. The idea under test: relax the Pareto frontier wi...
- Evaluating Interactivity: Toward Automated Assessment of AI-Generated Explorable Explanations
While large language models now enable rapid generation of interactive learning materials, evaluating the interaction quality of these explorable explanations remains an open challenge. Existing benchmarks largely focus on code executability or visual fidelity, providing limited insight into dynamic...
- A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems
Large language models are no longer only text generators. They are increasingly embedded in retrieval pipelines, enterprise assistants, coding environments, robotic systems, security-operation workflows, and autonomous agents that can read private data, call tools, write files, execute code, and act...
- Comparative Analysis of Machine Learning based Intrusion Detection in Realistic IoT Networks
The Internet of Things (IoT) is rapidly growing and expanding into various sectors, such as healthcare, transportation, smart homes, and more. Despite the benefits of using IoT devices, they present several challenges. Given the significant role these devices play in our lives, it is crucial to addr...
- EnclaveX: End-to-End Confidential AI with CPU/GPU TEEs
Large Language Models (LLMs) have rapidly proliferated, driving widespread adoption of AI applications. Most deployments rely on centralized infrastructures such as Microsoft Azure, Google Cloud, or AWS, requiring users to share sensitive data and training or fine-tuning code. This dependence raises...
- CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs
While post-training backdoor detection and trigger inversion schemes have been developed for AIs used e.g. for images, there is a paucity of such methods for LLMs. First, the LLM input space is discrete, with up to 150,000^k k-tuples to consider with k the token-length of a putative trigger. Second,...
- Probing Memorization of Tabular In-Context Learning
Large tabular models (LTMs), i.e., tabular foundation models leveraging in-context learning (ICL), achieve state-of-the-art performance on tabular tasks. While LLMs are known to unintentionally memorize training data, the memorization dynamics of LTMs remain largely unexplored. We investigate the po...
- An Empirical Study of Security Calibration in Large Language Models for Code
Large Language Models (LLMs) are rapidly transforming software development, yet their use in security-critical contexts raises a key question: do models know when their generated code is insecure? This property, known as calibration, measures whether a model's confidence aligns with the true correct...
- Secure-CHG: A Comprehensive Framework for Robust and Fair Federated Learning via Hybrid Defense and Contribution-Aware Trust
Federated Learning (FL) is highly susceptible to stealthy backdoor attacks, which aim to force a model into predicting an attacker-chosen target class for inputs containing a specific trigger. However, existing statistical defenses primarily focus on the early stages of model convergence. In this pa...
- Certified Speculative Execution for Untrusted AI Agents
Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a learned policy or a frozen LLM forfeits the feasibility guarantee a trusted solver provides, while invoking the solver at every step forfeits the speed...
- Hybrid Topological Data Analysis and LSTM Networks for Enhanced Network Intrusion Detection Using CIC-IDS2017 Dataset
Network intrusion detection systems (NIDS) are crucial in cybersecurity infrastructure, needing advanced techniques to detect hostile activity in network traffic. This research introduces a hybrid approach that combines Topological Data Analysis (TDA) with Long Short-Term Memory (LSTM) networks to i...
- No Prompt, No Leaks: A Robust Generative Steganography Framework via Prompt-Free Diffusion
Generative image steganography synthesizes stego images directly from secret information to achieve inherent security advantages. Latent Diffusion Models (LDMs) have recently emerged as a fundamental image steganography framework that modulates secret latent representations with text prompts. Limite...
- Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
The fast growth of open-source AI infrastructure, from model serving engines and agent platforms to the Model Context Protocol (MCP) ecosystem and the language models themselves, has outpaced the security tooling available to defend it. We present AI-Infra-Guard, an open-source framework that organi...
- Probe Choice Changes Canary-Memorization Verdicts: Three Post-Hoc Disagreement Case Studies in a Text-Dominant LoRA-Tuned Autoregressive Testbed
We audit a fixed prefix-window mean-NLL memorization probe (K=20) on a Qwen2.5-VL-7B canary testbed and report three post-hoc cases where it disagrees with full-span secret NLL or greedy exact-recall. C3 (false negative, window truncation): damage lands on hex tokens outside K=20; the probe stays fl...
- Do Machines Struggle Where Humans Do? LLM and Human Comprehension of Obfuscated Code
While code obfuscation impairs human code comprehension, it remains unclear if large language models share these failure modes. Building directly on a recent human study of program comprehension under code obfuscation, we evaluate whether large language models share the failure modes that obfuscatio...
- AdaTrans: Automated C to Rust Transformation via Error-Adaptive Repair
The automated transformation of C code to Rust is challenging due to Rust's strict ownership and borrowing semantics. While Large Language Models (LLMs) show promise, they often produce code that violates these rules or relies on unsafe constructs. We propose AdaTrans, a framework that addresses the...
- Failure-Based Testing for Deep Reinforcement Learning Agents
Deep Reinforcement Learning (DRL) agents have been widely adopted across diverse domains to address challenging decision-making problems, such as autonomous driving and robotic control. Given that many of these applications are safety- and security-critical, rigorous testing of DRL agents is indispe...
- MOA: A Profiling-Guided LLM Framework for Memory-Optimization Automation at Codebase Scale
Modern large-scale software systems often suffer from pervasive memory inefficiencies (e.g., bloat, churn), leading to excessive resource costs and performance degradation. Existing optimization workflows lack end-to-end automation, forcing developers to manually synthesize complex tool outputs into...
- FeatX: Editing Software by Editing Features for Repository-Level Code Evolution
Large language models (LLMs) are increasingly used for software evolution, yet most interaction paradigms remain code-centric and require manual context management and prompt iteration. We present FeatX, a feature-oriented tool for editing software by editing features. Given an existing repository, ...
- CoCoMUT: A Tool for Code-Context Mining and Automated Dataset Generation
Software-engineering assistants often need method-level context beyond an isolated body, including enclosing-class information, documentation, callers, callees, type hierarchy, and structural characteristics. Manually collecting this context is time-consuming, inconsistent, and difficult to reproduc...
- ScratchWorld: Evaluating If World Models Compute Executable Consequences
World-model evaluations often score a predicted future by overlap with a target state or observation. In sparse-change worlds, this can turn copied persistent state into apparent accuracy. We introduce ScratchWorld, an offline diagnostic benchmark that treats Scratch projects as executable worlds an...
- FormIDEAble: Safe and Socially-aware Autonomous Systems
Autonomous agents operating in socio-critical settings must coordinate with humans under uncertainty while respecting explicit safety constraints. Existing approaches either account for social dynamics without formal guarantees or provide formal assurance while abstracting away human behaviour. We i...
- A Self-Negotiation Framework for Ethical Decision-Making during Task Interruptions in Service Robots
Service robots operating in public environments frequently encounter interruptions when multiple users request service simultaneously. Resolving such conflicts requires ethical decision-making, as prioritizing one user request can disadvantage another. Current approaches rely on static rules or cent...
- FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model
Spoken language models (SLMs) extend LLMs to speech input and output. Existing SLMs represent speech at fixed frame rates (e.g., 25 or 12.5 Hz), ignoring the time-varying information density of speech and offering no flexibility to trade off quality for speed at inference time. Recent audio tokenize...
- Attacking UTMOS: Probing the Robustness of a Speech Quality Assessment Model
UTMOS has become one of the most commonly used deep neural network-based speech quality assessment (SQA) metrics in speech processing research. In this paper, we attack UTMOS to probe its robustness. Starting from high-quality speech samples, we optimize the input in two directions: a score-preservi...
- A Fair and Transparent Framework for Speech-Based Depression Detection: Balancing Interpretability and Performance
While speech provides rich, non-invasive biomarkers for mental-health assessment, clinical adoption is limited by opaque models and potential demographic bias. In this work we propose a methodological framework to evaluate robustness and interpretability for automated depression detection on the ext...
- Improving multichannel speech enhancement through accurate room-acoustic simulations
Room-acoustic simulations are widely used to augment training data for deep-learning-based speech enhancement. While most pipelines rely on simplified geometrical acoustics, wave-based approaches offer greater physical accuracy. In this work, we examine how simulation fidelity affects multichannel s...
- How Bilingual Are SSL Speech Models? Cross-Lingual Probing of Articulatory Encoding with Finnish and Russian EMA
SSL speech models capture rich phonetic, prosodic, and acoustic patterns from raw audio, yet how they encode articulatory information across diverse languages remains unclear. Using EMA data from bilingual Finnish-Russian speakers, we evaluate cross-lingual correlations between SSL latent representa...
- Beyond Cross-Reconstruction: Probing-Based Disentanglement Evaluation for Acoustic Teleportation Codecs
Some neural audio codecs disentangle speech into latent subspaces encoding content, speaker identity, and acoustics, enabling acoustic teleportation and voice conversion. Existing evaluations rely on cross-reconstruction quality, which cannot reliably detect leakage across partitions. We extend a pr...
- Beyond Binary Instrument QA: Probing Instrument Grounding in Music Audio-Language Models
Recent music audio-language models achieve high accuracy on instrument question-answering benchmarks, but it remains unclear whether this reflects robust audio grounding or benchmark-specific shortcuts. In this paper, we introduce an OpenMIC-derived diagnostic benchmark sequence for instrument groun...
- SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation
Diffusion-based text-to-audio (TTA) models achieve impressive synthesis quality but suffer from high inference latency due to iterative multi-step denoising. Existing one-step approaches alleviate this issue but still rely on paired text--audio data during distillation. To address these limitations,...
- UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling
Speech editing aims to modify specific portions of an utterance while preserving the remaining speech. Existing approaches primarily focus on word-level content modification and typically treat content, speaker, and emotion editing as separate tasks, limiting both editing granularity and flexibility...
- Reference-Based Prosody and Rhythm Evaluation for Spoken Dialogue Systems
Speech-to-speech (S2S) AI agents are advancing rapidly, yet evaluation lacks interpretable speech-native measures for conversational prosody and rhythm. Because $F_0$, speaking rate, articulation rate, and pausing shift with model-predicted speaker traits and interaction state, pooled human statisti...
- Usage frequency and application variety of research methods in library and information science: Continuous investigation from 1991 to 2021
The present study analyzed over 26,000 research articles published between 1991 and 2021 in twenty-one major LIS (Library and Information Science) journals, using the machine learning (ML) approach to categorize the research methods used by LIS scholars. The findings of this study are significant. F...
- Unsupervised Data-Efficient Cross-Modal Retrieval with Global-Neighborhood Alignment Hashing
Compared to supervised cross-modal hashing (CMH), unsupervised CMH reduces the reliance on manual labeling by learning binary codes from unlabeled image-text pairs. However, existing unsupervised CMH methods often rely on large-scale image-text pairs, which are costly to collect. To address this lim...
- One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG
RAG systems retrieve documents optimized for answering one query at a time. Yet enterprise users arrive with sessions, that is, coherent episodes of related questions that span semantically distant parts of the knowledge base. We show that a single retrieval call over a standard knowledge base cover...
- GenPage: Towards End-to-End Generative Homepage Construction at Netflix
We present GenPage, an end-to-end generative approach to Netflix homepage construction that replaces the traditional multi-stage recommender stack with a single transformer. GenPage treats the user and request context as a prompt, and autoregressively generates the entire structured, multi-row homep...
- NLP Framework for Automated Symptom Severity Staging in Heart Failure and COPD Clinical Notes Using Ontology Integration: A Study Protocol
Background: Heart failure (HF) and chronic obstructive pulmonary disease (COPD) are among the leading causes of morbidity and mortality globally, with effective management heavily dependent on accurate severity staging using the New York Heart Association (NYHA) and Global Initiative for Chronic Obstructive Lung Disease (GOLD) classification systems. However, severity information is frequently embedded within unstructured clinical narratives rather than standardized Electronic Health Record (EHR) fields, limiting automated clinical decision support, disease surveillance, and retrospective healthcare analytics. Existing Natural Language Processing (NLP) approaches primarily rely on rule-based keyword extraction or supervised deep learning methods requiring large annotated corpora, which are often unavailable in many healthcare settings. Equally, most current systems inadequately integrate clinical ontologies for semantic reasoning and explainable classification, limiting interoperability and clinical applicability. Objective: This study aims to develop and evaluate an ontology-integrated NLP framework for automated extraction and severity staging of HF and COPD symptoms from de-identified clinical notes using NYHA and GOLD classification systems. Methods: The study will employ a Design Science Research (DSR) methodology to design, implement, and evaluate a hybrid NLP framework integrating rule-based extraction, SNOMED-CT ontology reasoning, and a Bidirectional Long Short-Term Memory with Conditional Random Field (Bi-LSTM-CRF) deep learning architecture for clinical sequence labeling. Approximately 1,000 de-identified clinical notes will be sampled proportionately from publicly available repositories including MIMIC-III/IV, eICU Collaborative Research Database, AmsterdamUMCdb, and MTSamples. Clinical text preprocessing will include tokenization, lemmatization, dependency parsing, abbreviation expansion, and negation detection. Ontology-guided semantic normalization will map extracted symptom entities to standardized SNOMED-CT concepts to support severity staging. Framework performance will be evaluated using precision, recall, F1-score, Cohens Kappa, sensitivity, specificity, positive predictive value, negative predictive value, confusion matrices, and correlation analyses against confirmed diagnoses and guideline-based severity classifications. Expected Outcomes: The proposed framework is expected to automate NYHA and GOLD severity staging across heterogeneous clinical note types without reliance on manually annotated severity labels. The ontology-integrated architecture is anticipated to improve semantic consistency, interpretability, and explainability of NLP outputs while enhancing EHR analytics, retrospective clinical audit, and AI-assisted clinical decision support. Conclusion: Findings from this study may provide a scalable and transferable framework for automated severity classification in data-rich but label-poor healthcare environments.
- Enhancing Title and Abstract Priority Screening Through SimEd AI Pipeline.
The exhaustive identification of evidence is central to systematic reviews, but the screening of titles and abstracts remains particularly labor intensive. Priority screening, an active learning approach that ranks records by estimated relevance, has emerged as an effective strategy to reduce screening workload. Its efficiency is commonly quantified using work saved over sampling at 100% recall (WSS@100%), representing the percentage reduction in effort compared with random screening. Although modern priority-screening models achieve high efficiency on many benchmark datasets, some reviews still exhibit low WSS@100%, indicating suboptimal retrieval. Our study sought to improve the retrieval of all relevant articles in challenging datasets to ensure better generalization of priority screening. We first showed using SYNERGY benchmark datasets that while the most advanced ELAS_h3 priority screening model from state-of-the-art ASReview LAB v.2 open-source software, efficiently retrieved most relevant articles, it struggled with the rare, final ones in challenging datasets. To address this, we tested a hybrid approach entitled SimEd AI: using ELAS_h3 for early retrieval and then applying supervised fine-tuning to the biomedical transformer BioMed-RoBERTa-base with these relevant articles to enhance the detection of the remaining difficult cases. We found that fine-tuning BioMed-RoBERTa-base model with 10 late-identified relevant and 10 hard irrelevant study titles and abstracts, enabled faster retrieval of articles of interest compared to ELAS_h3 alone. This approach increased WSS@100% from 46.5% (SD0.0%) to 83.3% (SD0.4%), while adding only an average of 22 minutes of computational time for fine-tuning and inference. The SimEd AI priority screening pipeline could be valuable for situations requiring highest possible recall. It could be particularly useful in scoping reviews with broad or diverse topics where traditional priority screening methods may miss subtle relevance signals. Further work should define a data-driven stopping rule for ending screening once the fine-tuned domain-specific transformer is applied at the final stage and assess generalizability across additional challenging datasets.