AI News Archive: May 21, 2026 — Part 20
Sourced from 500+ daily AI sources, scored by relevance.
- Making the Discrete Continuous: Synthetic RAW Augmentations for Fine-Grained Evaluation of Person Detection Performance in Low Light
Real-world deployment of AI vision models is both fueled and limited by the data available for training and testing. Real datasets are sparse and uneven: long-tailed or unbalanced distributions hinder generalization, and the low number of samples in low density regions makes it hard to run evaluatio...
- Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts
While large vision-language-action (VLA) models and generative world models (WM) have advanced long-horizon embodied intelligence, their practical deployment remains challenged by uncertainty in learning-based action generation. Low-quality actions may cause physical failures during execution or lea...
- Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration
Exploration is a prerequisite for learning useful behaviors in sparse-reward, long-horizon tasks, particularly within 3D environments. Curiosity-driven reinforcement learning addresses this via intrinsic rewards derived from the mismatch between the agent's predictive model of the world and reality....
- The Matching Principle: A Geometric Theory of Loss Functions for Nuisance-Robust Representation Learning
Robustness, domain adaptation, photometric and occlusion invariance, compositional generalisation, temporal robustness, alignment safety, and classical anisotropic regularisation are usually treated as separate problems with separate method families. This paper argues that much of their shared struc...
- LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
Large language model (LLM)-based multi-agent systems increasingly rely on intermediate communication to coordinate complex tasks. While most existing systems communicate through natural language, recent work shows that latent communication, particularly through transformer key-value (KV) caches, can...
- Cyber-Physical Anomaly Detection in IoT-Enabled Smart Grids Using Machine Learning and Metaheuristic Feature Optimization
Modern smart grids rely on dense measurement infrastructures, communication links, and intelligent field devices. Although this improves supervision and control, it also increases vulnerability to cyber-physical disruptions. Operators must distinguish physical incidents, such as faults or line distu...
- Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning
Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This failure stems from the dominant single-agent paradigm for physical applications, where other actors are ignored or treated as environmental noise, pr...
- Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier
Real-world sensor-based learning systems require uncertainty estimation that is both reliable and computationally efficient. Evidential Deep Learning (EDL) provides single-pass uncertainty estimation by modeling the class probabilities via Dirichlet distributions, where the Dirichlet parameters are ...
- SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation
Parameter-efficient fine-tuning enables fast personalization of text-to-image diffusion models, but composing multiple custom concepts remains challenging due to representation interference. Existing modular methods either rely on expensive post-hoc fusion or freeze adaptation subspaces, which limit...
- Proxy-Based Approximation of Shapley and Banzhaf Interactions
Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these higher-order interactions trade off between speed and accuracy. To overcome this limitation, we introduce ProxySHAP. ProxySHAP reconciles the high sam...
- Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation
Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed through their loss functions: maximum likelihood, policy gradients, forward KL, reverse KL, or related objective-level variants. We study a complementary ...
- Reading Task Failure Off the Activations: A Sparse-Feature Audit of GPT-2 Small on Indirect Object Identification
We report a small, reproducible audit of which sparse-autoencoder (SAE) features of GPT-2 small fire differently on failed versus successful trials of the Indirect Object Identification (IOI) task. On 300 prompts, GPT-2 small reaches 79.7% accuracy; 146 of the 24,576 features in the layer-8 residual...
- Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators
Interactive streaming music generation promises the use of generative models for live performance and co-creation that is impossible with offline models. However, SOTA models exist in the discrete-AR regime, requiring industrial levels of compute for both training and inference. In this work, we inv...
- Abstraction for Offline Goal-Conditioned Reinforcement Learning
Markov Decision Processes (MDPs) often exhibit significant redundancy due to symmetries and shared structure across state-goal pairs in real-world Goal-Conditioned Reinforcement Learning (GCRL). While hierarchical policies have been motivated for horizon reduction via temporal abstraction in offline...
- Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a central paradigm for scaling LLM reasoning, yet its optimization often suffers from training instability and suboptimal convergence. Through a systematic dissection of clipping-based GRPO-style objectives, we identify the rigid c...
- ChronoVAE-HOPE: Beyond Attention -- A Next-Generation VAE Foundation Model for Specialized Time Series Classification
Time Series Foundation Models (TSFMs) have become a new component of the state-of-the-art in general time series forecasting. However, adapting them to specialized classification tasks remains constrained by two interconnected challenges: the quadratic cost of standard attention mechanisms and the i...
- Holographic functions and neural networks
A fuzzy Boolean function is a map $f:\cube^n\to [0,1]$, where $n\in\mathbb N$. We introduce and compare three ways of saying that such a function has bounded complexity. The first is a sampling property: the value $f(x)$ can be recovered, up to small error and with high probability, from the values ...
- A note on convergence of Wasserstein policy optimization
Wasserstein Policy Optimization (WPO) is a recently proposed reinforcement learning algorithm that leverages Wasserstein gradient flows to optimize stochastic policies in continuous action spaces. Despite its empirical success, the theoretical convergence properties of WPO in environments with conti...
- Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery
Recent LLM-guided evolutionary search methods have shown that iterative program mutation can discover strong algorithms, but they typically optimize each task independently, even when related tasks share reusable structure. We introduce Evolutionary Multi-Task Optimization (EMO) for LLM-guided progr...
- Healthcare LLM Benchmarks Are Only as Good as Their Explicit Assumptions
Benchmarks are necessary for healthcare evaluation, but are not sufficient for predicting deployment performance. Our position is that the evaluation--deployment gap arises not because of poorly designed benchmarks, but from implicit assumptions about how users interact with models that cannot be su...
- Benchmarking Machine Learning Architectures for Antimicrobial Stewardship in Pediatric ICUs
Antimicrobial stewardship (AMS) is critical in pediatric intensive care units (PICUs), where diagnostic uncertainty often drives broad-spectrum antibiotic use, increasing antimicrobial resistance and potential long-term harms. Machine learning offers a promising approach for identifying patient-leve...
- Innovations in Cardless Artificial Intelligence Banking: A Comprehensive Framework for Cyber Secure and Fraud Mitigation using Machine Learning Algorithms
The advent of cardless artificial intelligence (AI) banking heralds a paradigm shift in the financial landscape, offering users unprecedented security and convenience. This paper outlines a comprehensive framework designed to enhance cybersecurity, introduce auto-generated virtual cards, and mitigat...
- Novi Notes 1.1
A local AI memory layer for your Mac
- Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?
While deep ensembles are widely considered to be the default method for uncertainty quantification in deep learning, their effectiveness for graph-structured data is often simply assumed based on successes in domains like computer vision. We investigate standard deep ensembles specifically for messa...
- Integrable Elasticity via Neural Demand Potentials
We propose the Integrable Context-Dependent Demand Network (ICDN), a demand-first neural model for multiproduct retail demand. The model learns log-demand as a smooth, context-conditioned function of log-prices, allowing elasticities to be derived exactly from the learned demand surface. On the Domi...
- MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-driven update ships a fix. Self-evolving agents have emerged in response, but all confine evolution to text-mutable artifacts -- skill files, ...
- FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly Detection
Production systems generate millions of log lines daily, yet most anomaly detectors operate at the session or window-level, flagging groups of lines rather than identifying the specific message responsible. This coarse granularity forces operators to inspect many routine lines per alert. Message-lev...
- SDPM: Survival Diffusion Probabilistic Model for Continuous-Time Survival Analysis
Survival analysis aims to estimate a time-to-event distribution from data with censored observations. Many existing methods either impose structural assumptions on the hazard function or discretize the time axis, which may limit flexibility and introduce approximation errors. We propose the Survival...
- MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data
Real-time cognitive load assessment from eye-tracking signals could potentially enable adaptive human-centered-AI such as safety-critical applications such as driver vigilance monitoring or automated flight deck assistance, yet two challenges persist: handling frequent data missingness from blinks a...
- CogAdapt: Transferring Clinical ECG Foundation Models to Wearable Cognitive Load Assessment via Lead Adaptation
Real-time cognitive load assessment is essential for adaptive human-computer interaction but remains challenging due to limited labeled data and poor cross-subject generalization. Recent ECG foundation models pre-trained on millions of clinical recordings offer rich representations, but cannot be di...
- Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
Discrete diffusion models are often trained through clean-data prediction, but the prediction can be used in different ways to define the reverse dynamics. In Masked Diffusion Models (MDM) these choices largely coincide, whereas in Uniform Diffusion Models (UDM) they do not. We show that the standar...
- The Distillation Game: Adaptive Attacks & Efficient Defenses
Distillation attacks create a deployment trade-off for model providers: the same outputs that make a model more useful can also make it easier to imitate. We study this trade-off through a minimax game between a utility-constrained teacher and an adaptive student. Our framework yields tractable one-...
- Multiple Neural Operators Achieve Near-Optimal Rates for Multi-Task Learning
We study the approximation and statistical complexity of learning collections of operators in a shared multi-task setting, with a focus on the Multiple Neural Operators (MNO) architecture. For broad classes of Lipschitz multiple operator maps, we derive near-optimal upper bounds for approximation an...
- The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler
A central error measure in Gaussian DDPMs is the path-space KL divergence between the exact reverse chain and the learned Gaussian reverse process. This quantity is especially relevant for procedures such as classifier guidance, which perturb the entire reverse trajectory rather than only the termin...
- Posterior Collapse as Automatic Spectral Pruning
We show that posterior collapse in $β$-VAEs implements automatic spectral pruning. A latent mode collapses if its contribution to reconstruction is below the cutoff set by $β$. Equilibrium solutions with different $β$ thus reveal a cascade of collapses as latent modes decouple from least to most use...
- UNAD+: An Explainable Hybrid Framework for Unknown Network Attack Detection
The detection of previously unseen network attacks remains a major challenge for intrusion detection systems. Although supervised learning methods often perform well on known attack classes, they are limited when new attack types are not represented in the training data. Unsupervised methods are mor...
- MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
Learning real-world dynamics from visual observations is crucial for various domains. A common strategy is to calibrate simulators by estimating physical parameters, yet accuracy is ultimately bounded by the underlying physical models, which often assume materials are homogeneous and isotropic. Even...
- Factored Diffusion Policies:Compositionally Generalized Robot Control with a Single Score Network
Robotic tasks are typically specified by a tuple of factors, such as the object to be grasped, the obstacles to be avoided, the color of the target, and so on. Collecting expert demonstrations for every combination of factor values grows combinatorially. We present factored diffusion policies: a sin...
- Tycoon AI
Run one-person companies entirely with AI agents
- AutoSubtitles 2.0
AI subtitles & animated captions with faster editing
- App Store Operator
The App Store MCP for developers who never leave Claude
- PlatformPilot
Give your company a brain that evolves and acts.
- libraryai
Don’t read books alone
- Stable Audio 3.0
Generative audio model family for full compositions
- ResearchOS
AI-native end-to-end market research
- Super Benji
AI outbound that builds real conversations
- BotWork
AI Agent Freelance Network
- SirDash.ai
Ask your data anything. Get answers, not tickets.
- VIDI
AI contract risk analysis before you sign
- Qwen-3.7 Max
Cross harness foundation model for long running tasks