AI News Archive: May 19, 2026 — Part 26
Sourced from 500+ daily AI sources, scored by relevance.
- X-Ray cardiac angiographic vessel segmentation based on pixel classification using machine learning and region growing
This work proposes a pixel-classification approach for vessel segmentation in x-ray angiograms. The proposal uses textural features such as anisotropic diffusion, features based on the Hessian matrix, mathematical morphology and statistics. These features are extracted from the neighborhood of each ...
- Cardiac fat segmentation using computed tomography and an image-to-image conditional generative adversarial neural network
In recent years, research has highlighted the association between increased adipose tissue surrounding the human heart and elevated susceptibility to cardiovascular diseases such as atrial fibrillation and coronary heart disease. However, the manual segmentation of these fat deposits has not been wi...
- Stage-adaptive Token Selection for Efficient Omni-modal LLMs
Omni-modal large language models (om-LLMs) achieve unified audio-visual understanding by encoding video and audio into temporally aligned token sequences interleaved at the window level. However, processing these dense non-textual tokens throughout the LLM incurs substantial computational overhead. ...
- A Nash Equilibrium Framework For Training-Free Multimodal Step Verification
Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable limitations. Learned critics need extensive labeled data and show inconsistent performance across different tasks. Meanwhile, existin...
- InterLight: Leveraging Intrinsic Illumination Priors for Low-Light Image Enhancement
Low-Light Image Enhancement (LLIE) has long been a challenging problem in low-level vision, as insufficient illumination often leads to low contrast, detail loss, and noise. Recent studies show that deep learning-based Retinex theory can effectively decouple illumination and reflectance. However, ex...
- Towards Fine-Grained Robustness: Attention-Guided Test-Time Prompt Tuning for Vision-Language Models
Vision-Language Models (VLMs), such as CLIP, have achieved significant zero-shot performance on downstream tasks with various fine-tuning adaptation methods. However, recent studies have proven that adversarial attacks can significantly degrade the inference ability of VLMs, posing substantial risks...
- Gartner Forecasts Worldwide AI Spending to Grow 47% in 2026
Gartner Forecasts Worldwide AI Spending to Grow 47% in 2026 Gartner
- Gartner Survey Shows Just 36% of Chief Procurement Officers Are Very Confident in Ability to Redesign Function for AI
Gartner Survey Shows Just 36% of Chief Procurement Officers Are Very Confident in Ability to Redesign Function for AI Gartner
- Gartner Survey Finds AI Saves Sellers Nearly 5 Hours Per Week, Yet 72% of Sales Organizations Fail to Reinvest Time in High-Value Activities
Gartner Survey Finds AI Saves Sellers Nearly 5 Hours Per Week, Yet 72% of Sales Organizations Fail to Reinvest Time in High-Value Activities Gartner
- Gartner Survey Shows 31% of Chief Sales Officers Cited Difficulty Proving ROI of AI-driven Tools as a Top Challenge for Sales Objectives in 2026
Gartner Survey Shows 31% of Chief Sales Officers Cited Difficulty Proving ROI of AI-driven Tools as a Top Challenge for Sales Objectives in 2026 Gartner
- Gartner HR Research Reveals AI Will Create More Jobs Than It Eliminates Beginning in 2028
Gartner HR Research Reveals AI Will Create More Jobs Than It Eliminates Beginning in 2028 Gartner
- Announcing Claude Managed Agents on Cloudflare
Cloudflare has integrated with Anthropic's Claude Managed Agents to provide a fast, isolated execution environment for autonomous code delivery. This means builders can scale agent workflows globally while strictly controlling access to private backends and easily customizing their agent’s tools and runtimes.
- Google increases SynthID access to identify AI-generated content
Google increases SynthID access to identify AI-generated content The National
- Google SynthID comes to Chrome, Search, and ChatGPT. Users can right-click to check for AI content.
At Google I/O 2026, the company announced it's expanding its SynthID digital watermark, and OpenAI announced it's adopting it, too
- Atoms of Thought: Universal EEG Representation Learning with Microstates
Learning universal representations from electroencephalogram (EEG) signals is a cutting-edge approach in the field of neuroinformatics and brain-computer interfaces (BCIs). Conventionally, EEG is treated as a multivariate temporal signal, where time- or frequency-domain features are extracted for re...
- A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents
Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a first-class architectural object. This paper names that boundary the stochastic-deterministic boundary (SDB): a four-part contract among a proposer, ver...
- Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
Reinforcement learning with verifiable rewards has made post-training highly effective when correctness can be checked automatically. However, many important model behaviors require satisfying several qualitative criteria at once. Rubric-based rewards address this setting by grading prompt-specific ...
- Less Back-and-Forth: A Comparative Study of Structured Prompting
Large language models (LLMs) are widely used for open-ended tasks, but underspecified prompts can lead to low-quality answers and additional interaction. This paper studies whether structured prompt design improves response quality while reducing user effort. We compare three prompt conditions: a ra...
- Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
Speculative decoding (SD) accelerates large language model inference by leveraging a draft-then-verify paradigm. To maximize the acceptance rate, recent methods construct expansive draft trees, which unfortunately incur severe VRAM bandwidth and computational overheads that bottleneck end-to-end spe...
- ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions
Conversational AI has now reached billions of users, yet existing datasets capture only what people say, not what they think. We introduce ThoughtTrace, the first large-scale dataset that pairs real-world multi-turn human--AI conversations with users' self-reported thoughts: their reasons for sendin...
- What Do Evolutionary Coding Agents Evolve?
Recent work pairs LLMs with evolutionary search to iteratively generate, modify, and select code using task-specific feedback. These systems have produced strong results in mathematical discovery and algorithm design, yet a fundamental question remains: what do they actually evolve? Progress is typi...
- BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation
Large language models (LLMs) can enhance factuality via retrieval-augmented generation (RAG), but applying RAG to every query is unnecessary when the model-only answer is reliable. This motivates cascaded RAG: each query is first handled by an LLM-only branch, escalated to a RAG fallback only if the...
- VL-DPO: Vision-Language-Guided Finetuning for Preference-Aligned Autonomous Driving
The rapid growth of autonomous driving datasets has enabled the scaling of powerful motion forecasting models. While large-scale pretraining provides strong performance, the standard imitation objective may not fully capture the complex nuances of human driving preferences. Meanwhile, recent advance...
- CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning
Chain-of-thought (CoT) is a standard approach for eliciting reasoning capabilities from large language models (LLMs). However, the common CoT paradigm treats thinking as a prerequisite for answering, which can delay access to plausible answers and incur unnecessary token costs even when the model is...
- Probing Embodied LLMs: When Higher Observation Fidelity Hurts Problem Solving
Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to explain success or failure in closed-loop embodied tasks. Following an empirical AI methodology, we study embodied LLM agents behaviorally by varying ...
- Towards LLM-Assisted Architecture Recovery for Real-World ROS~2 Systems: An Agent-Based Multi-Level Approach to Hierarchical Structural Architecture Reconstruction
Explicit software architecture models are essential artifacts for communicating, analyzing, and evolving complex software-intensive systems. In ROS~2-based robotic systems, however, structural (de-)composition and integration semantics are often only implicitly encoded across distributed artifacts s...
- PromptRad: Knowledge-Enhanced Multi-Label Prompt-Tuning for Low-Resource Radiology Report Labeling
Automatic report labeling facilitates the identification of clinical findings from unstructured text and enables large-scale annotation for medical imaging research. Existing rule-based labelers struggle with the diverse descriptions in clinical reports, while fine-tuning pre-trained language models...
- When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity
Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentage points across diverse domains. Yet the same benchmarks show wide variance, with 16 of 84 tasks suffering negative delt...
- Training Neural Networks with Optimal Double-Bayesian Learning
Backpropagation with gradient descent is a common optimization strategy employed by most neural network architectures in machine learning. However, finding optimal hyperparameters to guide training has proven challenging. While it is widely acknowledged that selecting appropriate parameters is cruci...
- LLM Benchmark Datasets Should Be Contamination-Resistant
Benchmark datasets are critical for reproducible, reliable, and discriminative evaluation of LLMs. However, recent studies reveal that many benchmark datasets are included in pretraining corpora, i.e., $\textit{contaminated}$, which diminishes their value as reliable measures of model generalization...
- Block-Sphere Vector Quantization
Vector quantization is a fundamental primitive for scalable machine learning systems, enabling memory-efficient storage, fast retrieval, and compressed inference. Recent rotation-based quantizers such as EDEN, RabitQ, and TurboQuant have introduced strong guarantees and empirical performance, but th...
- Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes
Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perplexity-based detectors. We cast adversarial suffix detection as an online change-point detection problem over the token-level next-token entropy stream...
- A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits
While empirical scaling laws for LLM reasoning are well-documented, the theoretical mechanisms governing out-of-distribution (OOD) generalization remain elusive. We formalize reasoning via optimal transport, projecting discrete trajectories into a continuous metric space to quantify domain shifts us...
- Probabilistic Tiny Recursive Model
Tiny Recursive Models (TRM) solve complex reasoning tasks with a fraction of the parameters of modern large language models (LLMs) by iteratively refining a latent state and final answer. While powerful, their deterministic recursion can lead to convergence at suboptimal solutions, without escape me...
- PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across invocations, existing approaches preserve either the agent's trajectory, passive access to raw material, or task-level strategies. None of them preser...
- Fast and Featureless Node Representation Learning with Partial Pairwise Supervision
We introduce Contrastive FUSE, a fast and unified framework for scalable node representation learning in graphs with partially available pairwise node labels and no available node features. Unlike existing methods, we directly optimize a spectral contrastive objective that integrates community-aware...
- Composer 2.5
Cursor’s most powerful model yet
- StableGrad: Backward Scale Control without Batch Normalization
Training very deep neural networks requires controlling the propagation of magnitudes across depth. Without such control, activations and gradients may vanish, explode, or enter unstable regimes that make optimization fail. Modern architectures often mitigate this problem through Batch Normalization...
- A Framework for Evaluating Zero-Shot Image Generation in Concept-based Explainability
Concept-based Explainable Artificial Intelligence (XAI) interprets deep learning models using human-understandable visual features (e.g., textures or object parts) by linking internal representations to class predictions, thereby bridging the gap between low-level image data and high-level semantics...
- HaorFloodAlert: Deseasonalized ML Ensemble for 72-Hour Flood Prediction in Bangladesh Haor Wetlands
Flash floods in Bangladesh's haor wetlands show up with almost no warning. They wreck the annual boro rice harvest. Current setups, built for riverine floods, miss backwater dynamics entirely. These basins are flat. Water does not behave like it does on the Brahmaputra. We built HaorFloodAlert, a ...
- Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models
Large Vision Language Models (LVLMs) show promise in medical applications, but their inability to faithfully ground responses in visual evidence raises serious concerns about clinical trustworthiness. While visual attribution methods are widely used to explain LVLM predictions, whether these explana...
- Beyond Prediction Accuracy: Target-Space Recovery Profiles for Evaluating Model-Brain Alignment
Artificial vision models are often evaluated against the human visual cortex by measuring how accurately their internal representations predict brain responses. However, prediction accuracy alone does not indicate which dimensions of the target brain's response space are recovered. Here, we introduc...
- Using Aristotle API for AI-Assisted Theorem Proving in Lean 4: A Formalisation Case Study of the Grasshopper Problem
AI-assisted theorem proving can now generate substantial Lean developments for olympiad-level mathematics, but the evidential status of such developments depends on which declarations are actually verified. This paper reports a Lean 4 formalization case study of an Aristotle API proof attempt for th...
- Toto 2.0: Time Series Forecasting Enters the Scaling Era
We show that time series foundation models scale: a single training recipe produces reliable forecast-quality improvements from 4M to 2.5B parameters. We release Toto 2.0, a family of five open-weights forecasting models trained under this recipe. The Toto 2.0 family sets a new state of the art on t...
- k-Inductive Neural Barrier Certificates for Unknown Nonlinear Dynamics
While conventional (k=1) discrete-time barrier certificate conditions impose strict safety constraints by requiring the function to be non-increasing at every step, k-inductive barrier certificates relax this by allowing a temporary increase -- up to k-1 times, each within a threshold $ε$ -- while m...
- Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction
JEPAs often regularize one-view embeddings toward an isotropic Gaussian, implicitly baking Euclidean symmetry into the representation. We show that this is not merely a benign default. For a known structured downstream geometry $H\succ0$, the minimax and maximum-entropy covariance under a Hamiltonia...
- Neurosymbolic Learning for Inference-Time Argumentation
Claim verification is an important problem in high-stakes settings, including health and finance. When information underpinning claims is incomplete or conflicting, uncertain answers may be more appropriate than binary true or false classifications. In all cases, faithful explanations of the conside...
- INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification
Discovering shapelets -- i.e., discriminative temporal patterns within time series -- has been widely studied to address the inherent complexity of time-series classification (TSC) and to make model decision-making processes more transparent. However, existing methods primarily focus on population-l...
- Probability-Conserving Flow Guidance
Diffusion and flow-based generative models dominate visual synthesis, with guidance aligning samples to user input and improving perceptual quality. However, Classifier-Free Guidance (CFG) and extrapolation-based methods are heuristic linear combinations of velocities/scores that ignore the generati...
- AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail and inform the next attempt, and lessons accumulate across cycles. Existing autonomous research systems often model this...