AI News Archive: May 18, 2026 β Part 16
Sourced from 500+ daily AI sources, scored by relevance.
- Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation
Commonly available prior information, such as BIM models, floor plans, and remote sensing images, can provide valuable geometric and semantic context for autonomous robotic systems. In this paper, we treat observations from fixed external RGB cameras as Common Prior Maps (CPMs): wide-field views of ...
- TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
In real home deployments, household agents must often operate from a complete household scene and a situated household request, rather than from a clean task specification. Such requests require agents to identify task-relevant entities, recover intended task conditions, and resolve ordering constra...
- Confidence-Gated Robot Autonomy: When Does Uncertainty Actually Help?
Robotic systems often use predictive uncertainty to decide whether to act autonomously or defer to a fallback policy. In threshold-gated autonomy, uncertainty matters mainly through its ability to rank likely errors. Standard metrics such as expected calibration error and AUROC do not directly test ...
- See Silhouettes in Motion with Neuromorphic Vision
Quasi-bimodal objects, such as text, road signs, and barcodes, play a basic yet vital role in daily visual communication. By boiling these down to clear silhouettes, binarization uses a minimal language to convey essential vision cues for maximum downstream efficiency. The catch is that frame-based ...
- Active Defense Against False Data Injection Attacks in Robotic Manipulators
Robotic systems are vulnerable to False Data Injection Attacks (FDIAs), where adversaries corrupt sensor signals to gain malicious control. Feedback linearization exposes robotic systems to integrator vulnerability, making them susceptible to stealthy attacks that can cause significant deviations in...
- TacSE3: Equivariant SE(3) Motion Estimation from Low-Texture Visuotactile Images for In-Gripper Tracking and Compensation
Robotic in-hand manipulation requires reliable object-motion tracking under frequent visual occlusion, yet low-texture visuotactile images provide few stable correspondences for conventional image- or geometry-matching methods. This paper presents TacSE3, a tactile motion-estimation pipeline that co...
- Learning-Based Adaptive Control for Surgical Robotic Exposure Task on Deformable Tissues
In various surgical procedures, regions of interest (ROIs) such as organs or lesions are often occluded by overlying tissues, requiring surgeons to achieve adequate exposure for precise intervention. However, the irregular geometry, nonlinear biomechanical properties of overlying tissues, and limite...
- WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform
World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, existing embodied world model benchmarks are still largely confined to vision-only prediction, offline embodied applicatio...
- Virtues of Ordered Chaos: Planning with Topple Actions in Tabletop Stack Rearrangement
Efficient object manipulation strategies have significant impact in automation applications. In this work, the stack rearrangement in tabletop settings is studied, with a focus on augmenting the task planning domain with richer nonprehensile aggregating actions, in particular the toppling of objects...
- Orlume
AI that builds websites that looks crafted by top designers.
- Canonical Regularisation of Wide Feature-Learning Neural Networks
Wide neural networks in the feature-learning regime drive modern deep learning, and yet they remain far less studied than their kernel-regime counterparts. We consider a critical yet under-explored difference between these two regimes: the regulariser and prior implied by gradient flow training. Thi...
- Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method
Muon has recently emerged as a strong alternative to AdamW for training neural networks, with encouraging large-scale pretraining results and growing evidence that matrix-structured updates can be faster in practice. Yet Muon, and more generally Linear Minimization Oracle (LMO) based methods, are ty...
- Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers
A striking geometric disparity has long persisted in the practice of deep learning. While modern neural network architectures naturally exhibit rich symmetry and equivariance properties, popular optimizers such as Adam and its variants operate inherently coordinate-wise, rendering them unable to res...
- Uncertainty Reliability Under Domain Shift: An Investigation for Data-Driven Blood Pressure Estimation in Photoplethysmography
Uncertainty quantification (UQ) is critical for safety-critical domains like healthcare, yet it is rarely evaluated under realistic out-of-distribution (OOD) conditions. Here, we assessed predictive performance and uncertainty reliability for deep learning-based blood pressure (BP) estimation from p...
- Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew
Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks. Nonetheless, current TDA approaches lack reliability and robustness, preventing their adoption in real-world setups. In this paper, we take a decisive step towards more r...
- Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models
Self-distillation has emerged as a promising technique for improving model performance in modern machine learning systems. We develop the statistical foundations of self-distillation in spiked covariance models, by introducing and analyzing a broad class of estimators, namely spectral shrinkage esti...
- Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
We study feature learning in two-layer neural networks within the linear-width regime, where the number of hidden neurons, sample size, and input dimension scale proportionally. While recent work has analyzed feature learning via a single step of gradient descent, such updates are fundamentally limi...
- StatQAT: Statistical Quantizer Optimization for Deep Networks
Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes, selecting optimal quantization parameters remains a key cha...
- How does feature learning reshape the function space?
Feature learning is widely regarded as the key mechanism distinguishing neural networks from fixed-kernel methods, yet its impact on the induced function space remains poorly understood. In this work, we precisely characterize how the function space spanned by the features of a two-layer neural netw...
- EA Engine AI
Turn Trading Strategy Videos Into Trading Robots π€
- Folio
Private AI Β· Subscriptions
- AI MathScanner: Exact Layout OCR
1:1 layout math scanner. Export to native Word OMML & LaTeX.
- AgentID
One identity, memory & inbox for every AI agent you run
- WorkGeniusPro
AI-powered all-in-one business operating System
- HypeCheck
AI reality checks for startup ideas
- BestAIapp
Find the best AI tool for your exact job
- Native App AI
Turn any website/app into a Play Store-ready app in minutes
- rails-mcp
Allows AI agents to eval and verify rails/ruby code changes
- Astras AI
A New Startup Company Located in Bangalore
- LifeFile Pro
Your Smart A.I enhanced Fintech digital vault
- Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster
Discrete diffusion models are a powerful class of generative models with strong performance across many domains. For efficiency, however, discrete diffusion typically parameterizes the generative (reverse) process with factorized distributions, which makes it difficult for the model to learn the tar...
- Wasserstein bounds for denoising diffusion probabilistic models via the FΓΆllmer process
This paper studies sampling error bounds for denoising diffusion probabilistic models (DDPMs) in the 2-Wasserstein distance. Our contributions are threefold. (i) Under general Lipschitz-type conditions on the score function and for a broad class of variance schedules, including the cosine schedule, ...
- A note on connections between the FΓΆllmer process and the denoising diffusion probabilistic model
The FΓΆllmer process is a Brownian motion conditioned to have a pre-specified distribution at time 1. This process can be interpreted as an "augmented" time-compressed version of the reverse stochastic differential equation (SDE) for the denoising diffusion probabilistic model (DDPM). While this fact...
- Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
Highly over-parameterized models can simultaneously memorize noisy labels and generalize well, yet how these behaviors coexist remains poorly understood. In this work, we investigate the underlying mechanisms of this coexistence using modular arithmetic tasks under heavy label noise. Through extensi...
- A data-driven Fourier-mixture neural-network method for density estimation
We propose a data-driven Fourier-trained neural-network method for estimating fixed-horizon probability densities from empirical characteristic-function (CF) information. The estimator is a positive Gaussian--Laplace mixture with closed-form CF, so training can be performed directly in Fourier space...
- From Saddle Points Toward Global Minima: A Newton-Type Method on Wasserstein Space
We study the minimization of non-convex functionals over the Wasserstein space. While recent work has showed that perturbed Wasserstein gradient methods can avoid saddle points for benign landscapes, existing approaches remain essentially first-order and do not provide fast local convergence once th...
- Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
iffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sample quality on task-specific objectives. However, most existing techniques require repeated score or gradient evaluations, introducing bias, high comput...
- A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows
We develop a unified theoretical framework for data-free one-step sampling from unnormalized target distributions based on Wasserstein gradient flows. For a broad class of standard f-divergence objectives, we show that the induced velocity field admits the universal form $\mathbf{V}(x)=w(r(x))\,Ξ²(x)...
- Online Conformal Prediction for Non-Exchangeable Panel Data
Panel data, in which multiple units are repeatedly observed over time, arise throughout science and engineering. Quantifying predictive uncertainty in such settings is challenging because conformal prediction, while distribution-free and model-agnostic, classically relies on exchangeability assumpti...
- LobeHub
Your Chief Agent Operator for multi-agent work
- Shadow
AI computer screen and voice control with custom automation
- Searchad.ai
Run Apple Search Ads by Chatting with AI
- M1 by Montage
Agentic UI that scales on demand
- Polarity
The Self-Improvement Stack For agents
- Krea 2
An image model built for style control and moodboards
- Draft
Capture AI chats into your knowledge base
- LandingHero AI
24/7 Salesperson on Your Website
- Triggered Agents by Adaptive
AI agents that run automatically on business events
- pixserp
Your LLM on the live web. One endpoint, ten answer shapes.
- Voiser AI
Human-like AI voiceovers in 140+ languages