AI News Archive: May 26, 2026 — Part 20
Sourced from 500+ daily AI sources, scored by relevance.
- Enabling Extensible Embodied Capabilities with Tools
Most existing embodied intelligence methods formulate perception, reasoning, planning, and control within a unified parameterized policy. Yet these capabilities are inherently hierarchical and heterogeneous, making them difficult to reliably learn and modularize within a single model. We propose a c...
- Provably Safe Motion Planning Under Unknown Disturbances
We present a provably safe sampling-based motion planning algorithm for robotic systems affected by random disturbances of unknown distribution. We consider systems with linear or linearizable dynamics evolving in workspace with arbitrary-shaped obstacles subject to state and control constraints. Sa...
- Multi-Robot Box Transport over Different Surfaces with Decentralized Role-based Proportional Control
Collaborative transport of objects via pushing by multiple robots has many applications, ranging from construction and warehouse environments to post disaster debris clean-up. Achieving collaborative transport over surfaces with different inclination and friction properties however poses unique chal...
- Sampling Data with Chains of Forward-Backward Diffusion Steps
Sampling from learned high-dimensional distributions is a foundational computational problem. We introduce U-turn chains: Markov chains obtained by iterating short forward-backward steps of a diffusion model, in which each step proposes a move that remains on the learned data manifold and, paired wi...
- Signal-to-Noise Ratio and Sample Size Govern Representational Alignment in Neural Networks
Neural networks are known to develop latent representations that are $aligned$, namely structurally similar across networks trained with different architectures, training protocols, or training datasets. We study this phenomenon in a controlled setting, where we train an ensemble of networks on regr...
- Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models
Normalization layers in modern large language models (LLMs) consist of a deterministic normalization operation and a learnable scale vector. While the normalization operation has been extensively studied, the scale vector remains poorly understood despite its ubiquitous use. In this work, we present...
- Transformers Can Learn Posterior Predictive Distributions In-Context
Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive distribution (PPD) through in-context learning. Despite their strong empirical performance and ability to go beyond point predictions, theoretical unde...
- Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
Reinforcement learning (RL) often has a hierarchical structure, where an upper-level (UL) learner selects model parameters and a lower-level (LL) decision-making process responds, naturally leading to a bilevel optimization problem. Most existing bilevel RL methods assume a single-policy LL Markov d...
- More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations
Feedforward network (FFN) layers account for a large fraction of parameters and nonlinear expressivity in Transformer-based large language models (LLMs). Despite the evolution from ReLU and GELU to gated variants such as SwiGLU, most FFN designs still use a single fixed activation function, applying...
- Few-shot Cross-country Generalization of Tabular Machine Learning and Foundation Models for Childhood Anemia Prediction under Distribution Shift
Childhood anemia affects around 40% of children aged 6-59 months globally and arises from heterogeneous factors, limiting model generalizability. We evaluate a transformer-based tabular foundation model against classical supervised methods under cross-country and data-scarce settings. We used DHS ...
- Structure-Adaptive Conformal Inference for Large-Scale Out-of-Distribution Testing
This paper addresses structured out-of-distribution (OOD) testing in high-stakes machine learning applications. Traditional conformal methods rely on joint exchangeability, making it difficult to incorporate auxiliary information such as spatiotemporal or grouping structures. To overcome this limita...
- Constrained Bayesian Experimental Design via Online Planning
Bayesian experimental design (BED) is a principled framework for data-efficient design of sequential experiments. However, existing BED methods are unable to adapt to dynamic constraints inherent in real-world tasks due to budget limitations, varying costs, or physical constraints that restrict how ...
- Agile Online Model Selection: Resolving Adaptation Lag via Safeguarded Large Learning Rates
Maintaining predictive accuracy in non-stationary environments requires online model selection to adapt autonomously to unknown distribution shifts. However, existing tuning-free algorithms face a fundamental trade-off between robustness and agility. Specifically, to ensure dynamic regret bounds, th...
- SpecDD
Build better software with spec-driven AI
- Sample Complexity of Policy Gradient for Log-Growth Control
We study the sample complexity of policy gradient for log-growth control -- the problem of learning, from observed state transitions, a feedback gain that optimally stabilizes a scalar linear system driven through a multiplicative-noise actuation channel. The objective $J(K) = \mathbb{E}[\log|1+BK|]...
- Function-Valued Causal Influence in Nonlinear Time Series
Causal discovery in time series is increasingly performed using nonlinear machine-learning models, yet the resulting causal relationships are almost always summarized by scalar edge scores. We argue that this practice obscures the true object learned by nonlinear autoregressive models: a state-depen...
- Brew
Like Claude design for email marketing
- Parrot Speech-to-text API
Fast, accurate STT for production-grade voice agents
- AVTR-1 Real-Time Open Weights Model
Generating uncanny AI avatars is now open source
- Willow Scribe
Tell Scribe what to say. It writes the rest.
- SelectPrism
Agents that screen and interview so you can hire faster
- DodoForm
Turn talking, pics, or scribbles into clean, structured data
- Parsewise API
API for agentic multi-document processing
- LangPanda
Learn languages from watching your favorite shows
- Kept
Your AI chats, saved as Markdown locally with no cloud
- marpy.io
AI coding platform built specifically for the Python stack
- MiniCPM5-1B
A new SOTA for compact open models on the edge
- Ormedo
Let AI agents handle your entire outbound pipeline
- Ajar
Lid Angle Sync & Keep Awake for AI Agents on Mac
- Hayley: Your Thinking Companion
An insight, a pattern, one question worth sitting with.
- NoteCove
Notes, tasks, and AI — offline-first, no SaaS bill.
- AI Shadowing
Turn any YouTube video into a language shadowing lesson
- ReplylessAI Sequences
Outbound email sequences without the sales-tool bloat
- Prava Pay
Give your AI Agent a one-time card to make payments-safely
- Summit AI Notes
Local-first meeting notes with full data ownership.
- Wicely
Your autonomous R&D analyst
- Whizo AI
Your Agency on Autopilot.
- AdminForth
Agent-first open-source admin panel framework
- Mira
Your agentic exit interviewer
- KOBI
Your team's second brain — but it actually remembers
- NeonShade Labs
Building offline-first AI models for threat intelligence
- PromptForge
Turn raw ideas into perfectly optimized AI prompts.
- AIVault
Free curated directory of the best AI tools for everyone
- Keith
College admissions AI App with a free Competition Index
- LearnPeng
Type any topic. Get an AI audio course in minutes.
- dhrive
dhrive turns a simple prompt into a real native iOS app
- Clearminutes
AI meeting notes that never leave your machine. 100% local.
- Madar
Compact codebase context for AI coding agents
- AI Badgr
Run AI apps with reliable APIs and GPU compute
- RPG Materia — Grimoire Academy
Cut Claude API costs 80% by playing an RPG. Free.