AI News Archive: May 13, 2026 — Part 24
Sourced from 500+ daily AI sources, scored by relevance.
- MUJICA: Multi-skill Unified Joint Integration of Control Architecture for Wheeled-Legged Robots
Wheeled-legged robots hold promise for traversing complex terrains and offer superior mobility compared to legged robots. However, wheeled-legged robots must effectively balance both wheeled driving and legged control. Furthermore, due to noisy proprioceptive sensing and real-world motor constraints...
- Local Conformal Calibration of Dynamics Uncertainty from Semantic Images
We introduce Observation-aware Conformal Uncertainty Local-Calibration (OCULAR), a conformal prediction-based algorithm that uses perception information to provide uncertainty quantification guarantees for unseen test-time environments. While previous conformal approaches lack the ability to discrim...
- Distributionally Robust Safety Under Arbitrary Uncertainties: A Safety Filtering Approach
In this work, we study how to ensure probabilistic safety for nonlinear systems under distributional ambiguity. Our approach builds on a backup-based safety filtering framework that switches between a high-performance nominal policy and a certified backup policy to ensure safety. To handle arbitrary...
- DynoJEPP: Joint Estimation, Prediction and Planning in Dynamic Environments
DynoJEPP is a factor-graph-based framework that jointly formulates and simultaneously optimizes estimation, prediction, and planning in dynamic environments. In conventional factor-graph-based approaches that jointly formulate estimation, prediction, and planning, information from prediction and pla...
- Learning Perturbations to Extrapolate Your LLM
Recent advancements in large language models demonstrate that injecting perturbations can substantially enhance extrapolation performance. However, current approaches often rely on discrete perturbations with fixed designs, which limits their flexibility. In this work, we propose a framework where t...
- Unified generalization analysis for physics informed neural networks
Physics-Informed Neural Networks (PINNs) and their variational counterparts (VPINNs) are neural networks that incorporate physical laws, making them useful for scientific problems. Existing generalization analyses for PINNs and VPINNs remain limited, often requiring restrictive assumptions such as s...
- Amortized Neural Clustering of Time Series based on Statistical Features
This paper introduces an algorithm-agnostic approach to feature-based time series clustering via amortized neural inference. By training neural networks to approximate the optimal partitioning rule from simulated data, the proposed framework reduces reliance on conventional clustering methods, such ...
- Adaptive Kernel Density Estimation with Pre-training
Density estimation in high-dimensional settings is an important and challenging statistical problem.Traditional methods based on kernel smoothing are inefficient in high dimensions due to the difficulties in specifying appropriate location-adaptive kernels. In this work, we introduce pre-training, a...
- Coreset-Induced Conditional Velocity Flow Matching
We propose Coreset-Induced Conditional Velocity Flow Matching (CCVFM), a generative model that augments hierarchical rectified flow with a data-informed source distribution. Hierarchical flow matching models the full conditional velocity law in velocity space, but its inner flow is asked to transpor...
- When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
LLM-enabled AI workflows increasingly produce outputs through iterative generate-evaluate-revise loops. Each iteration can improve the candidate, but it also creates a release decision: when to stop and output the current result? This raises a statistical challenge because deployment-time evaluator ...
- The Sample Complexity of Multiple Change Point Identification under Bandit Feedback
We study multiple change point localization under bandit feedback. An unknown piecewise-constant function on a compact interval can be queried sequentially at adaptively chosen inputs, and each query returns a noisy evaluation of the function. The goal is to identify a prescribed number of discontin...
- Coupling-Informed Transport Maps for Bayesian Filtering in Nonlinear Dynamical Systems
A likelihood-free transport filtering method is proposed based on the couplings between state and observation variables. By exploiting a block-triangular structure in the transport map, the analysis step of filtering is reformulated as the minimization of the maximum mean discrepancy (MMD) between t...
- Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
Modern Bayesian optimization and adaptive sampling methods increasingly rely on nonlinear parametric models, yet theoretical guarantees for such models under adaptive data collection remain limited. Existing analyses largely focus on Gaussian processes, kernel machines, linear models, or linearized ...
- Generative Modeling of Approximately Periodic Time Series by a Posterior-Weighted Gaussian Process
Discrete automated processes in industrial and cyber-physical systems often exhibit a repetitive structure in which successive repetitions follow a common trajectory while differing in duration, amplitude, and fine-scale dynamics. Such \emph{approximately periodic} behavior poses a challenge for Gau...
- State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives
Determinantal point processes (DPPs) have emerged as a kernelized alternative to vanilla independent sampling for generating efficient minibatches, coresets and other parsimonious representations of large-scale datasets. While theoretical foundations and promising empirical performance have been dem...
- The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
Weak-to-strong (W2S) generalization, in which a strong model is fine-tuned on outputs of a weaker, task-specialized model, has been proposed as an approach to aligning superhuman AI systems. Existing theoretical analyses either fix the student's representations or operate in restricted settings. Whe...
- Robust Sequential Experimental Design for A/B Testing
Experimental design has emerged as a powerful approach for improving the sample efficiency of A/B testing, yet existing designs rely critically on correctly specified models. We study robust sequential experimental design under model misspecification and develop a unified framework that covers both ...
- Memoket Gem
An AI wearable that remembers your conversations all day
- Latitude for Claude Code
See where Claude Code burns tokens. Hit your limits less.
- Frontdesk AI
AI COO to run your business like a Fortune 500 enterprise
- Googlebook
A new kind of laptop designed for Gemini Intelligence
- Blaze 2.0
AI marketer for SMBs complete w/ strategy, content, and ads
- Apideck MCP Server
Give AI agents access to real-time data across 200+ apps
- Liminary
Ground your AI in saved knowledge as you work
- Claudy
A proper home for Claude Code — multi-session, multi-account
- Pipali
An AI coworker for any computer work
- Whisper Internet Infra AI Context
Free MCP for security AI: live BGP, DNS, threat graph
- Crade AI
Like ChatGPT, but it sees your screen
- IMFS One
ERP, CRM, e-Invoicing, AI and Marketing.
- whyanalyst.ai
AI Data Analyst - data analysis ai tool
- LedgerBrain
Chain analysis for those who can't afford chainalysis
- WordFlip — Flip and Learn
The Smartest Way to Learn a Language
- Bizscal
The All-in-One AI Growth Engine for E-commerce SMEs.
- Rival.io
Run AI Faster. Build without the bloat.
- GrowZen AI
AI Growth Platform for Outreach, Automation&Lead Generation
- ReferralWorld Careers
AI-powered hiring, referrals & career platform for tech
- VIGILATE
Legal document summarizer. No jargon, just simple english
- ngram
Video agent for product and marketing teams
- Dualmark
Open-source AEO infrastructure for marketing sites
- Shellular
Your entire dev environment & coding agents on your phone.
- aifeed
Where AI tools and ideas get noticed
- AI-enabled Pointer
Point and speak to execute tasks on your screen
- Patronus Protect
On-device AI firewall — see and control AI traffic, locally
- Daybreak by OpenAI
Scan codebases, find vulnerabilities, and patch them with AI
- e2a – open-source email API for agents
Give your AI agents a real, authenticated email address.
- Grantbot.pl
Write EU grant proposals in minutes, not weeks
- FocusAI
Turn any goal into a step-by-step action plan
- AI Duel
Send your AI agent to an LLM prompt-injection arena
- LexFlag
AI-powered vendor risk and compliance screening platform
- baar-core
Stop LLM API bills before they happen — not after