NASA’s new AI space chip could let spacecraft think for themselves
NASA is testing a next-generation space computer chip that could give spacecraft the ability to operate far more independently in deep space. The radiation-hardened processor is showing performance levels hundreds of times beyond current spaceflight computers while surviving punishing tests designed...
Vision-Based Runtime Monitoring under Varying Specifications using Semantic Latent Representations
arXiv:2605.13923v1 Announce Type: new
Abstract: We study certified runtime monitoring of past-time signal temporal logic (ptSTL) from visual observations under partial observability. The monitor must infer safety-relevant quantities from images and provide finite-sample guarantees, while being \emp...
Your data engineers may be more influential than you think
The data engineer has gone from a largely behind-the-scenes role to one of the most strategically important positions in a modern technology organization. The leaders who understand why are making significantly better infrastructure decisions than the ones who do not.
Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity
arXiv:2605.12584v1 Announce Type: new
Abstract: Recently, multimodal graph learning (MGL) has garnered significant attention for integrating diverse modality information and structured context to support various network applications. However, real-world graphs are often isolated due to data-sharing...
CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks
arXiv:2605.12580v1 Announce Type: new
Abstract: Randomized neural networks (RdNNs) enable efficient, backpropagation-free training by freezing randomly initialized input-to-hidden weights, which permits a closed-form solution for the output layer. However, conventional random initialization is blin...
Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents
arXiv:2605.12620v1 Announce Type: new
Abstract: Building generalist embodied agents capable of solving complex real-world tasks remains a fundamental challenge in AI. Multimodal Large Language Models (MLLMs) have significantly advanced the reasoning capabilities of such agents through strong vision...
The future AI team: What enterprise AI organizations may look like by 2030
Ask most enterprises what their AI team looks like in 2030 and you will get a blank stare followed by a reference to their current headcount.
That is understandable. It is also a problem. Because the AI team of 2030 is going to look very little like the AI team of today...
New quantum algorithm solves “impossible” materials problem in seconds
A new quantum-inspired algorithm has cracked a problem so massive that conventional supercomputers struggle to even approach it. Researchers used the method to simulate extraordinarily complex quantum materials known as quasicrystals, opening the door to powerful new quantum devices and ultra-effici...
Your “um” and pauses could reveal early dementia risk
The little pauses, “ums,” and moments when you struggle to find the right word may reveal far more about your brain than anyone realized. Researchers discovered that everyday speech patterns are closely tied to executive function — the mental system that powers memory, planning, focus, and flexible ...
Interpretable EEG Microstate Discovery via Variational Deep Embedding: A Systematic Architecture Search with Multi-Quadrant Evaluation
arXiv:2605.10947v1 Announce Type: new
Abstract: EEG microstate analysis segments continuous brain electrical activity into brief, quasi-stable topographic configurations that reflect discrete functional brain states. Conventional approaches such as Modified K-Means operate directly in electrode spa...
arXiv:2605.10973v1 Announce Type: new
Abstract: Supervised fine-tuning (SFT) improves in-domain performance but can degrade out-of-domain (OOD) generalization. Prior work suggests that this degradation is related to changes in dominant singular subspaces of pretrained weight matrices. However, dire...
A Cascaded Generative Approach for e-Commerce Recommendations
arXiv:2605.11118v1 Announce Type: new
Abstract: Personalized storefronts in large e-commerce marketplaces are often assembled from many independent components: static themes per page section ("placement"), retrieval systems to fetch eligible products per placement, and pointwise rankers to order co...
RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Ranking
arXiv:2605.11151v1 Announce Type: new
Abstract: Offline-to-online reinforcement learning (RL) improves sample efficiency by leveraging pre-collected datasets prior to online interaction. A key challenge, however, is learning an accurate critic in large state--action spaces with limited dataset cove...
arXiv:2605.08360v1 Announce Type: new
Abstract: Modern AI is opening the door to collective decision-making in which participants express their views as free-form text rather than voting on a fixed set of candidates. A natural idea is to embed these opinions in a vector space so that the substantia...
Distributional Reinforcement Learning via the Cram\'er Distance
arXiv:2605.08104v1 Announce Type: new
Abstract: This paper explores the application of the Soft Actor-Critic (SAC) algorithm within a Distributional Reinforcement Learning setting and introduces an implementation of such algorithm named Cram\'er-based Distributional Soft Actor-Critic (C-DSAC). The ...
Where Reliability Lives in Vision-Language Models: A Mechanistic Study of Attention, Hidden States, and Causal Circuits
arXiv:2605.08200v1 Announce Type: new
Abstract: A pervasive intuition holds that vision-language models (VLMs) are most trustworthy when their attention maps look sharp: concentrated attention on the queried region should imply a confident, calibrated answer. We test this Attention-Confidence Assum...
Researchers Worldwide Compete to Shape the Future of AI in Organizations
More than 200 academic teams submitted proposals to the AI for Organizations Grand Challenge, exploring how artificial intelligence will transform teamwork and collaboration.
SocialReasoning-Bench: Measuring whether AI agents act in users’ best interests
Using SocialReasoning Bench, we observed a stable pattern across models—agents execute competently, but fail to consistently improve the user’s position, even with explicit instructions to optimize for user interest.
The post SocialReasoning-Bench: Measuring whether AI agents act in users’ best inte...
On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching
arXiv:2605.06680v1 Announce Type: new
Abstract: Flow matching generates data by integrating a learned velocity field, where the number of integration steps (NFE) directly determines inference cost. We analyze which properties of the velocity field govern integration error by decomposing the velocit...
arXiv:2605.05365v1 Announce Type: new
Abstract: We present ZAYA1-8B, a reasoning-focused mixture-of-experts (MoE) model with 700M active and 8B total parameters, built on Zyphra's MoE++ architecture. ZAYA1-8B's core pretraining, midtraining, and supervised fine-tuning (SFT) were performed on a full...