AI News Archive: May 27, 2026 — Part 21
Sourced from 500+ daily AI sources, scored by relevance.
- leania.ai
MRI scanner for Businesses: Find What to Cut, Replace, Automate
- SAFEVPR: Patch-Based Conformal Verification for Safe Cross-Condition Sequence Visual Place Recognition
Sequence-based visual place recognition (VPR) for SLAM and robot relocalization must decide whether the retrieved top-1 candidate is safe to accept. Conformal prediction is a natural framework for this accept/reject decision, but its finite-sample guarantees rely on exchangeability between calibrati...
- How Should We Teach Robots? A Comparison of Kinesthetic, Joystick, and Gesture-Based Teaching
Instructing robots from demonstrations can be done through different teaching modalities, each with different usability and performance trade-offs. This paper compares kinesthetic guidance, joystick teleoperation, and hand gestures in a user study with eight participants. We evaluate replay success,...
- Simultaneous Contact Selection and Planning for Contact-Rich Manipulation with Cascaded Optimization
We propose an optimization-based framework for robust contact-rich manipulation. Recent contact-implicit methods enable online hybrid planning across contact modes, allowing closed-loop manipulation for a given target state and contact location sequence of the robot and object. However, most existin...
- Con-DSO: Learning Short-Horizon Consistency Priors for RGB-D Direct Sparse Odometry
Visual odometry (VO) is a fundamental component in robotics and augmented reality. RGB-D direct VO benefits from metric depth measurements, but it can degrade in challenging environments, where dynamic objects, occlusions, illumination changes, and unreliable depth violate the short-horizon photomet...
- VLM-Based Advanced Rider Assistance System for Motorcycle Safety
Motorcycles face disproportionately high crash risks compared to cars due to limited protection and heightened sensitivity to surface hazards, yet Advanced Rider Assistance Systems (ARAS) remain underdeveloped relative to Advanced Driver Assistance Systems (ADAS). We propose a novel ARAS that enhanc...
- SANTS: A State-Adaptive Scheduler for World Action Models
World Action Models (WAMs) improve robot manipulation by using video-based future representations to condition action generation. In pixel-space WAMs, however, the best action condition is not necessarily the fully denoised video. Controlled denoising-depth scans show that video refinement can reduc...
- Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal
Learning visuomotor policies via behavior cloning typically involves mimicking expert demonstrations collected by human operators. However, natural human demonstrations inherently contain high-frequency noise, such as intermittent jerks, pauses, and action jitter. Training policies to directly imita...
- S-Cheetah: A Novel Quadrupedal Robot with a 3-DOF Active Spine Learning Agile Locomotion
The biological spine of quadrupeds enables sagittal flexion/extension, lateral bending, and axial rotation, playing a crucial role in highly agile and dexterous locomotion. While numerous studies have integrated active spinal joints into quadrupedal robots to enhance agility, most designs simplify c...
- Tabero: Learning Gentle Manipulation with Closed-Loop Force Feedback from Vision, Touch, and Language
Tactile sensing is essential for robots to achieve human-like gentle manipulation. However, existing Vision-Language-Action (VLA) models struggle to exploit tactile feedback for gentle manipulation due to scarce aligned vision-tactile-language data and the lack of effective closed-loop force feedbac...
- Turning Video Models into Generalist Robot Policies
Video generative models have emerged as a promising robotics backbone, capable of generating videos that depict the completion of complex tasks across embodiments and environments. Recent work proposes robot foundation models that jointly predict future observations and actions by finetuning video m...
- Deep Neural Networks for Doubly Robust Estimation with Nonprobability Survey Samples
Integrating probability and nonprobability survey samples is an important problem in modern survey sampling. Nonprobability samples often contain rich outcome information but may lack population representativeness, whereas probability samples provide design-based auxiliary information but may not co...
- Variance-Adaptive Optimal Algorithm for Reinforcement Learning with Multinomial Logit Function Approximation
Reinforcement learning with multinomial logistic (MNL) function approximation has become an important framework due to its flexibility and broad applicability. While existing studies have established regret guarantees under worst-case analysis, they do not capture how performance depends on the vari...
- Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings
Fairness-accuracy trade-offs are a central concern in the deployment of fairness-aware machine learning methods. When sensitive attributes are unavailable at inference time-the so called unawareness setting, principled methods for obtaining accurate predictions under relaxed fairness constraints are...
- Deep Neural Network Training as Random Effects: An Optimization-Inference Duality
Deep neural networks (DNNs) have achieved remarkable empirical success, yet their training dynamics remain understood mainly from optimization rather than statistical principles. Here we develop a statistical framework for DNN training in the over-parameterized regime by showing that the prediction ...
- Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
Generative models, including diffusion models, are increasingly used as foundation models and adapted through sequential fine-tuning, making continual learning an essential problem setting. However, continual learning in such generative models remains poorly understood: after a task change, what asp...
- contxt.to
Share context with your team and their AI - in one link.
- Multi-Teacher Knowledge Distillation via Teacher-Informed Mixture Priors
Knowledge distillation is a powerful method for model compression, enabling the efficient deployment of complex deep learning models (teachers), including large language models. However, its underlying statistical mechanisms remain unclear, and uncertainty evaluation is often overlooked, especially ...
- Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency
Backpropagation is the default learning rule for artificial neural networks and is often treated as the settled approach whenever differentiability is available. In this work, we revisit this convention through a theoretical lens of sample efficiency. We introduce a unified vectorized feedback frame...
- Reward Transfer from Inverse Reinforcement Learning: A Coupled Minimax Approach
We study the transfer of rewards learned using inverse reinforcement learning from expert demonstrations in one environment to reinforcement learning in a new, different environment. This arises naturally when demonstrations are collected in a controlled environment. We formulate the problem as a jo...
- Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learning
Many real-world classification tasks require predicting multiple labels per instance, necessitating the optimization of complex evaluation metrics such as the $F$-measure and Jaccard index. While the Empirical Utility Maximization (EUM) framework is natural for these population-level metrics, existi...
- Conservative neural posterior estimation via distributionally robust training
Simulation-based inference with neural posterior estimation (NPE) often yields overconfident and unreliable posteriors under limited simulation budgets. To address this, we propose DRO-NPE, a distributionally robust approach that replaces the standard NPE objective with a worst-case loss over a Wass...
- Latent Diffusion for Missing Data
Diffusion models have emerged as powerful generative approaches for missing-data imputation, yet most existing methods operate directly in data space and degrade when training data are heavily incomplete. We investigate whether shifting diffusion to a learned latent representation improves robustnes...
- Decision-focused learning for optimal PV-Battery scheduling
The use of residential photovoltaics has increased dramatically in recent years. With battery systems becoming more affordable, the optimal operation of a photovoltaic-battery system can bring significant savings to households. Optimal control requires correct forecasts of underlying parameters, suc...
- Insurance Pricing Optimization via Off-Policy Evaluation
Traditional insurance pricing relies on risk-based principles that ensure actuarial fairness and solvency but do not explicitly account for policyholders' price sensitivity. We formulate insurance pricing as a decision-making problem and study it using tools from off-policy evaluation and stochastic...
- Adaptive Bandit Algorithms for Contextual Matching Markets
We study bandit learning in matching markets, where players and arms constitute the two market sides, and the players' utilities are linear in the arm contexts. In each round, new arms arrive with observable contexts. Then, the algorithm matches them to players, aiming to minimize each player's regr...
- Parameter-Efficient Generative Modeling with Controlled Vector Fields
We introduce a continuous-time generative modeling framework, motivated by the Chow-Rashevskii theorem, that builds expressive flows from a small set of fixed vector fields and learned scalar controls. Instead of learning an unconstrained high-dimensional vector field, our framework constructs the v...
- Counterfactually Fair Regression via Optimal Transport
We consider the problem of learning a counterfactually fair regressor. We adopt a causal uncertainty view in which counterfactual fairness is defined with resampled noise. We focus on obtaining theoretical fairness guarantees for a new post-processing estimator. We begin by showing that counterfactu...
- Learning to Bid in Repeated Second-Price Auctions with Dynamic Values and Aggregated Feedback
We study the problem of learning to bid when the bidder's value is dynamic, i.e., when the current value depends on past outcomes. Specifically, we consider a bidder participating in repeated second-price auctions whose value depends on the time elapsed since their last successful bid, with auctions...
- The conditional-mean barrier: From deterministic regression to conditional distribution learning
Many problems in computational science and engineering become one-to-many after coarse graining, partial observation, or inverse reconstruction: a resolved state may not determine a unique subgrid forcing, a structural descriptor may not determine a unique effective response, and a low-resolution ob...
- Learning to target with network interference
This paper studies adaptive targeting under network interference in a bandit setting, where treatments applied to one individual may affect others through spillover effects. We consider a linear model in a sparse regime, where each individual's outcome can be affected by at most a few others. We fir...
- Bluedot 2.1
Record on Apple Watch. Sync with Claude
- Powabase
Build AI apps with Postgres, RAG, and agents
- zero.xyz
Give your AI agent access to ~8k tools, APIs and services
- Oasis Browser for Mac
A privacy-first AI browser you can train anonymously
- Coworker AI
More AI for less spend with context-aware model routing
- Octolane
Self-driving AI CRM that you can talk to
- Calling Skills for AI Agents
Add voice and video calling via your coding agent
- Pawse.ai
An acoustic regulation system for dogs
- Krater
All the AI tools you use, one subscription
- baz.studio
Skills library & video editor for AI Agents
- Extend
Parse any PDF layout with SOTA accuracy for AI pipelines
- BobCA
A sovereign agent that learns to code with your preferences
- BankStatementLab
Turn any bank statement PDF into Excel, CSV or JSON with AI
- Chunk sidecars
Validate agent-generated code before it ever reaches CI
- AI Product Adoption Deck
12 diagnostics, 80 action cards, 12 workshops - one workflow
- Agent Studio
Your local hub for agent-powered development
- HiveMind
Your team's AI knowledge base, connected to Slack
- Lumio
Personalized audio bedtime stories for kids - powered by AI
- Bonsai Image 4B
Run a 4B image model on your phone