AI News Archive: May 20, 2026 — Part 14
Sourced from 500+ daily AI sources, scored by relevance.
- Non-invasive Transcriptomic Cell Profiling of the Human Endometrium with Generative Deep Learning
Background Delineating the cellular origins of extracellular vesicles (EVs) enables the detection of clinically relevant changes in dynamic and complex tissues, such as the endometrium, which are not characterizable through single biomarker assays. Transcriptome deconvolution into cellular composition using deep learning methods provides a means to explore this complexity. However, such computational methods have not been previously applied to EV bulk transcriptomes, and their efficacy in profiling EV population changes and concordance to tissue throughout the menstrual cycle remains unknown. Methods This observational cross-sectional study utilized a deconvolutional generative deep learning algorithm, BulkTrajBlend, trained on a comprehensive human endometrial single-cell RNA sequencing (scRNA-seq) atlas. The model was applied to deconvolve paired bulk transcriptomes from endometrial tissue and uterine fluid EVs (UF-EVs) across the proliferative (P, n=4), early-secretory (ES, n=5), mi
- Benchmarking General-Purpose and Medical AI Large Language Models for Clinical Assessment and Management in Parkinson's Disease
Background: The clinical applicability of large language models (LLMs) in Parkinson's disease (PD) management remains insufficiently characterized, particularly in generative responses to clinical vignette scenarios. Objective: To evaluate the quality of clinical assessments and management plans generated by a general-purpose LLM (Gemini 1.5 Pro) and a medically specialized LLM (OpenEvidence), and to compare their performance. Methods: Models generated free-text responses to 45 open clinical queries, focused on assessment of the situation, and recommended management plan. Two movement disorders fellows rated outputs using 5-point Likert scales, dichotomized into clinically appropriate ([≥]4) versus inappropriate ([≤]3). Discrepancies were adjudicated by a senior movement disorders specialist. Paired comparisons used McNemar's test; qualitative analysis examined severe errors. Results: Gemini 1.5 Pro and OpenEvidence showed high rates of clinically appropriate assessments (80.0% vs. 86.
- Psychological Stress-Associated Ceramide and Diacylglyceride Lipotoxicity as Contributors to First Episode Depression Pathophysiology: A neuroimmune-Metabolic-Oxidative Stress (NIMETOX) Perspective
Background: Aberrations in neuro-immune, metabolic, and oxidative stress (NIMETOX) pathways are implicated in major depressive disorder (MDD). First-episode simple dysmood disorder (FE-SDMD) without metabolic syndrome offers a unique model to investigate early lipid alterations underlying NIMETOX pathophysiology. Methods: Plasma samples were collected from 88 university students (44 FE-SDMD, 44 healthy controls). Participants underwent comprehensive psychiatric and psychological assessments, including adverse childhood experiences (ACEs), negative life events (NLEs), depression, anxiety, suicidal behaviors, and insomnia. Untargeted lipid profiling was performed using LC-QTOF-MS, while indices of oxidative and nitrosative stress (ONS) and lecithin-cholesterol acyltransferase (LCAT) activity were assessed. Data was analyzed using machine learning approaches with recursive feature elimination and cross-validation. Results: FE-SDMD was characterized by increased ceramides (CER), diacylglyc
- ALARM-Net: An Event-Level False-Alarm Suppression Framework for Clinical EEG Seizure Detection on TUSZ v2.0.6
Automated electroencephalography (EEG) seizure detection systems support clinical monitoring through alarm-driven workflows, in which the practical utility of a detector is determined by its event-level false-alarm rate. We examine the false-alarm structure produced by a strong window-level seizure detector on the Temple University Hospital Seizure Corpus (TUSZ) v2.0.6 and find that the false-alarm burden is unevenly distributed across subjects, with worst-decile subjects carrying substantially higher FA/24h than the cohort median. We propose ALARM-Net (Alarm-Level Adaptive Rejection Module), a detector-agnostic event-level alarm-suppression framework. ALARM-Net treats the window-level detector as a frozen black box, generates high-recall event proposals from its per-second probability timeline, and applies a regularized CatBoost classifier over 14 causal features summarizing each proposal's probability morphology, local pre-context, and alarm history. Operating-point selection is gove
- Frontal Cortex-Subthalamic Nucleus Beta Oscillations Exhibit Phase Locking and Granger Causality in Parkinson's Disease
Objective. Pathological beta oscillations are a hallmark of Parkinson's Disease (PD) and are linked with symptom severity and therapeutic efficacy of deep brain stimulation (DBS). Although some studies suggest that beta oscillations may propagate from the frontal cortex to the subthalamic nucleus (STN), direct evidence based on cortical and subcortical neural recordings remains limited. This study investigates synchrony and directionality of beta-band interactions between the frontal cortex and STN in PD. Approach. Simultaneous electrocorticography and STN local field potential recordings were obtained from three PD patients undergoing awake DBS lead placement surgery. Cortical-STN beta phase synchrony was quantified using phase locking value, and directed functional connectivity was analyzed using time-resolved bivariate Granger causality. Main results. Phase locking value mapping revealed a spatially non-uniform distribution of beta phase synchrony, with the strongest coupling locali
- Smarter edits? Post-editing with error highlights and translation suggestions
As MT quality increases, interest in enhanced post-editing features such as QE-derived error highlights is growing, yet evidence for their usefulness remains limited. In this work, we explore the usefulness of LLM-derived error highlights and correction suggestions based on automatic post-editing (A...
- ACL-Verbatim: hallucination-free question answering for research
Academic researchers need efficient and reliable methods for collecting high-quality information from trusted sources, but modern tools for AI-assisted research still suffer from the tendency of Large Language Models (LLMs) to produce factually inaccurate or nonsensical output, commonly referred to ...
- WCXB: A Multi-Type Web Content Extraction Benchmark
Web content extraction - isolating a page's main content from surrounding boilerplate - is a prerequisite for search indexing, retrieval-augmented generation, NLP dataset construction, and large language model training. Progress in this area has been constrained by the limitations of existing evalua...
- LoCar: Localization-Aware Evaluation of In-Vehicle Assistants through Fine-Grained Sociolinguistic Control
While Large Language Models (LLMs) are increasingly integrated into in-vehicle conversational systems, identifying the optimal model remains challenging due to the lack of domain-specific evaluation standards tailored to real-world deployment requirements. In this paper, we propose a novel evaluatio...
- Fine-grained Claim-level RAG Benchmark for Law
The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answering paradigm, where users ask questions and LLMs generate responses. In high-stake domains such as law, retrieval-augmented generation (RAG) is commonly used to mitigate hallucinations in generated...
- APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings
Typical LLM responses tend to follow a default style, even though users often have distinct preferences regarding tone, verbosity, and formality that they do not explicitly state in their prompts. Evaluating whether personalization methods can adapt to these implicit preferences is challenging, sinc...
- Cross-lingual robustness of LLM-brain alignment and its computational roots
Large language models (LLMs) reliably predict neural activity during language comprehension and transformer depth has been interpreted as mirroring hierarchical cortical organization. However, it remains unclear whether such alignment extends to subcortical regions, overlaps spatially across languag...
- Building a Custom Taxonomy of AI Skills and Tasks from the Ground Up with Job Postings
Utilizing LLMs for automated taxonomy construction presents a clear opportunity for the comprehensive, yet efficient mapping of potentially complex domains. When contending with high volumes of rapidly growing corpora, however, it becomes unclear how to best leverage such data for optimal taxonomy c...
- Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs
Enterprise analytics aims to make organizational data accessible for decision-making, yet non-technical users still face barriers when using traditional business intelligence tools or Text-to-SQL systems. While recent Text-to-SQL approaches based on Large Language Models (LLMs) promise natural langu...
- Towards Context-Invariant Safety Alignment for Large Language Models
Preference-based post-training aligns LLMs with human intent, yet safety behavior often remains brittle. A model may refuse a harmful request in a standard prompt but comply when the same intent is wrapped in adversarial wording. We suggest that robust safety requires context-invariant alignment, wh...
- ArPoMeme: An Annotated Arabic Multimodal Dataset for Political Ideology and Polarization
Memes have become a prominent medium of political communication in the Arab world, reflecting how humor, imagery, and text interact to express ideological and cultural positions. Despite the centrality of memes to online political discourse, there is a lack of systematically curated resources for an...
- Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
Scaling conditional memory offers a promising way to increase language-model capacity, but existing methods such as Engram learn large memory tables from scratch during pre-training, making memory scaling expensive and sometimes ineffective. We propose Memory Grafting, a conditional memory scaling m...
- DASH: Fast Differentiable Architecture Search for Hybrid Attention in Minutes on a Single GPU
Hybrid attention architectures are becoming an increasingly important paradigm for improving LLM inference efficiency while preserving model quality, making hybrid architecture design a central problem. Existing designs often rely on manual empirical rules or proxy-based selector signals for layer-w...
- Strategy-Induct: Task-Level Strategy Induction for Instruction Generation
Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction induction demonstrates that LLMs can infer better instructions with limited examples, existing approaches often rely on input-output pairs, where obtaining...
- Octopus to Figma plugin
Generate website prototype from a sitemap project
- Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate
Hyperparameter transfer allows extrapolating optimal optimization hyperparameters from small to large scales, making it critical for training large language models (LLMs). This is done either by fitting a scaling law to the hyperparameters or by a judicious choice of parameterization, such as Maxima...
- AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists
Recent advances in artificial intelligence (AI) have accelerated the growth of both human-authored and AI-generated research outputs, placing increasing strain on traditional academic publishing systems and challenging the scalability of conference- and journal-centered paradigms amid rising submiss...
- WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata
Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, many real-world scenarios require external knowledge that is not directly observable in the image to answer correctly. We introduce WikiVQABench, a hum...
- Mem-$π$: Adaptive Memory through Learning When and What to Generate
We present Mem-$π$, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from external memory stores. Existing memory-augmented agents typically rely on similarity-based retrieval from episodic memory banks or skill ...
- Approximation Theory for Neural Networks: Old and New
Universal approximation theorems provide a mathematical explanation for the expressive power of neural networks. They assert that, under mild conditions on the activation function, feedforward neural networks are dense in broad function classes, such as continuous functions on compact subsets of $\m...
- Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs
Interpretable autonomous driving planners depend not only on generating explanations, but also on those explanations remaining reliable under real-world sensor degradation. In this paper we present a controlled perturbation study of Vision-Language-Action (VLA) robustness in autonomous driving, eval...
- torchtune: PyTorch native post-training library
Modern LLMs typically require multistage training pipelines to achieve strong downstream performance, with post-training serving as the main interface for adapting open-weight models. We introduce torchtune, a PyTorch-native library designed to streamline the post-training lifecycle of LLMs, enablin...
- PALS: Power-Aware LLM Serving for Mixture-of-Experts Models
Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While prior systems optimize throughput and latency by batching, scheduling, and parallelism, they largely treat GPU power as a static constraint ra...
- Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition
Blended emotion recognition is challenging because emotions are often expressed as mixtures of subtle and overlapping multimodal cues rather than a single dominant signal. We propose a rank-aware multi-encoder framework that selectively combines complementary representations from diverse pre-extract...
- Stdlib or Third-Party? Empirical Performance and Correctness of LLM-Assisted Zero-Dependency Python Libraries
Third-party Python libraries introduce dependency management overhead, supply chain risk, and deployment friction in constrained environments. A natural question is how much of this ecosystem can be replicated using only Python's standard library -- and at what correctness and performance cost. We a...
- Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment
Large language models (LLMs) are increasingly deployed as autonomous agents that make sequences of decisions over extended interactions in high-stakes domains. However, the behavior of LLMs under sustained authority pressure is still an open question with direct implications for the safety of agenti...
- Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G
The proliferation of emerging applications, such as autonomous driving and immersive experiences, demands cellular networks that are not only faster, but fundamentally more resilient and autonomous. This paper presents a BlueSky vision on how Artificial Intelligence will be natively integrated into ...
- Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training
Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to annotate and scene-biased, making real-synthetic co-training with near-infinite synthetic data a promising direction. Howe...
- Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents
Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterate. This process misses patterns that only emerge across trace populations and does not scale to production corpora where individual traces span tens o...
- SymbolicLight V1: Spike-Gated Dual-Path Language Modeling with High Activation Sparsity and Sub-Billion-Scale Pre-Training Evidence
Natively trained spiking language models struggle to combine Transformer-like language quality, stable multi-domain pre-training, and high activation sparsity. We present SymbolicLight V1, a spike-gated dual-path language model that combines binary Leaky Integrate-and-Fire spike dynamics with a cont...
- TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimization methods iteratively rewrite prompts using LLM-generated feedback, but the resulting prompts often become longer, accumulate narrow sample-speci...
- Frontier: Towards Comprehensive and Accurate LLM Inference Simulation
Modern LLM serving is no longer homogeneous or monolithic. Production systems now combine disaggregated execution, complex parallelism, runtime optimizations, and stateful workloads such as reasoning, agents, and RL rollouts. Simulation is attractive for exploring this growing design space, yet exis...
- DeCoR: Design and Control Co-Optimization for Urban Streets Using Reinforcement Learning
Modern vision systems can detect, track, and forecast urban actors at scale, yet translating perception outputs to urban design remains limited. We introduce DeCoR, a two-stage reinforcement learning framework that leverages flow observations to co-optimize crosswalk layout and network-level signal ...
- From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
Mechanistic interpretability produces circuit-level causal analyses of neural network behaviour, but discovered circuits often remain isolated experimental artefacts: there is no shared formal representation for what circuits compute, how they relate, or when two findings provide evidence for the sa...
- TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health
Longitudinal passive sensing enables continuous health prediction, yet models often fail under cross-dataset distribution shifts. Traditional ML overfits cohort-specific artifacts, while Large Language Models (LLMs) struggle to reason reliably over long, heterogeneous time-series. We introduce TimeS...
- \textit{Stochastic} MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent
Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but struggle with multimodal action distributions. Generative policies are more expressive, but often require iterative samplin...
- How Much Online RL is Enough? Informative Rollouts for Offline Preference Optimization in RLVR
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for reasoning in language models, with GRPO as its primary example. However, GRPO requires continuous online rollout generation, making it computationally expensive and difficult to scale. While Direct Preferenc...
- Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
Current 3D-aware pretraining methods for embodied perception and manipulation are largely built on differentiable rendering frameworks, producing either fully implicit neural fields or fully explicit geometric primitives. Implicit representations, while expressive, lack explicit structural cues, whe...
- APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
LLM agents have shown strong performance across a wide range of complex tasks, including interactive environments that require long-horizon decision making. But these agents cannot learn on the fly at test time. Self-evolving agents address this by accumulating memory and reflection across episodes ...
- PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment
We address the problem of making a pre-trained reinforcement learning (RL) policy safety-aware by incorporating cost constraints without retraining it from scratch. While costs could be numerically encoded, we assume a more general setting is when costs are provided as preferences. Given a reward-op...
- Artificial Intelligence Reshapes Microwave Photonics
As a rapidly emerging interdisciplinary field that intrinsically integrates microwave and photonics, microwave photonics (MWP) provides disruptive solutions to overcome the fundamental bandwidth of conventional electronic systems. By exploiting the inherently ultra-wide bandwidth and low-loss charac...
- Behavior-Consistent Deep Reinforcement Learning
Reinforcement learning (RL) often exhibits high variance across training runs, leading to unreliable performance and posing a major challenge to deployment in real-world domains. In this work, we address the challenge of cross-run policy divergence by formalizing the problem of behavior-consistent R...
- Enhanced Reinforcement Learning-based Process Synthesis via Quantum Computing
In this work, we present quantum reinforcement learning (RL) as a solution strategy for process synthesis problems. Building on our prior work, we develop a generalized framework that formally poses process synthesis as a Markov decision process and introduces quantum-enhanced RL algorithms to solve...
- Variance Reduction for Expectations with Diffusion Teachers
Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution. The teacher gradients these pipelines consume are Monte Carlo (MC) expectations over noise levels and Gaussian noise samples; their estimator variance...
- Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling
Computer-use agents (CUA) automate tasks specified with natural language such as "order the cheapest item from Taco Bell" by generating sequences of calls to tools such as click, type, and scroll on a browser. Current implementations follow a sequential fetch-screenshot-execute loop where each itera...