Brain-inspired chip runs near absolute zero and could transform quantum computing
Scientists at the University of Hong Kong have created a remarkable new type of brain-inspired chip that can function just above absolute zero, one of the coldest environments imaginable. By using a standard silicon carbide transistor in a completely new way, the team made a single device behave lik...
Few-Shot Resampling for Scalable Statistically-Sound Data Mining
arXiv:2606.11235v1 Announce Type: new
Abstract: A key step in knowledge discovery is the evaluation of data mining results. In several applications, including pattern mining, graph analysis, and others, this step includes the evaluation of the statistical significance of the results, to avoid spuri...
Exploratory Responsiveness and Adaptive Rigidity under AI-Assisted Optimization
arXiv:2606.10086v1 Announce Type: new
Abstract: This paper develops a theory of exploratory adaptation under AI-assisted optimization. The central argument is that the long-run adaptive effects of AI systems depend critically on how predictive assistance interacts with exploratory responsiveness it...
Predictive Assistance and the Temporal Dynamics of Exploratory Compression
arXiv:2606.10094v1 Announce Type: new
Abstract: Classical theories of cognition describe problem solving as exploratory search through structured problem spaces in which repeated interaction gradually compresses search into efficient representational structures. Predictive artificial intelligence s...
Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark
arXiv:2606.07550v1 Announce Type: new
Abstract: Offline reinforcement learning (RL) offers a promising route for developing plasma controllers from historical tokamak data, since online trial-and-error on real devices is costly and risky. However, progress in this direction remains difficult to mea...
A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline
arXiv:2606.07718v1 Announce Type: new
Abstract: Agentic AI tools offer a promising path to automating software development bottlenecks in scientific research pipelines, particularly for stages that take domain experts days to months to build, where scientists care about correctness and robustness, ...
Why Limit the Residual Stream to Layers and Not Tokens? Persistent Memory for Continuous Latent Reasoning
arXiv:2606.07720v1 Announce Type: new
Abstract: Large language models (LLMs) have demonstrated remarkable reasoning abilities on mathematical and multi-hop planning tasks. The CoCoNuT (Chain of Continuous Thought) paradigm~\cite{hao2024coconut} extends this by enabling models to reason in latent sp...
Multi-Scale Feature Attention Network for Polymer Classification using THz Dual-Comb Spectroscopy
arXiv:2606.06554v1 Announce Type: new
Abstract: Reliable polymer identification is essential for ensuring the quality and safety of recycled plastics, yet conventional sorting and spectroscopic techniques often struggle to deliver robust discrimination. Terahertz Dual-Comb Spectroscopy (THz-DCS) of...
WAV: Multi-Resolution Block Residual Routing for Deep Decoder-Only Transformers
arXiv:2606.06564v1 Announce Type: new
Abstract: Residual connections are central to training deep Transformers, but standard PreNorm residual streams aggregate sublayer updates with fixed unit weights. Recent Attention Residuals replace this fixed accumulation with content-dependent depth-wise rout...
Detecting and Mitigating Bias by Treating Fairness as a Symmetry Operation
arXiv:2606.06514v1 Announce Type: new
Abstract: Machine learning systems deployed in high stakes socioeconomic settings routinely display bias. We formalize bias as a symmetry breaking operation: a classifier is fair if its outputs remain invariant under the counterfactual operation of switching a ...
Today's AI Talks Like “Nobody.” New Research Gives It Real Personality.
PsychAdapter lets researchers dial in on personality traits, age, and mental health characteristics to generate text that sounds like real individuals, opening the door to training simulations and personalized content.
Boards want AI roadmaps. Competitors are shipping AI features. And 74% of companies still can't make it pay. This piece breaks down the eight-point framework that separates disciplined AI adoption from expensive noise.
PyCC.id: A package for hypothesis-driven equation discovery with structural identifiability
arXiv:2606.05191v1 Announce Type: new
Abstract: Data-driven equation discovery is fundamentally an inverse problem that seeks to infer the governing differential equations of a system directly from time-series measurements. A known issue is the ill-conditioned nature of the inverse problem, which f...
Early Detection of Alzheimer's Disease Using Explainable Machine Learning on Clinical Biomarkers: A Multi-Class Classification Study Using the Alzheimer's Disease Neuroimaging Initiative (ADNI) Dataset
arXiv:2606.03995v1 Announce Type: new
Abstract: Background: Alzheimer's disease (AD) affects over 55 million people worldwide. Accurate, interpretable detection of normal cognition (NC), mild cognitive impairment (MCI), and AD from routine clinical assessments remains a critical unmet need. Methods...
Novel Aspects of IEEE SA P3109 Arithmetic Formats for Machine Learning
arXiv:2606.04028v1 Announce Type: new
Abstract: The IEEE P3109 draft standard defines a parameterized family of binary floating-point formats and associated operations, with a focus on facilitating machine learning. These formats allow efficient and consistent representation of values in a small nu...
Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent
arXiv:2606.04031v1 Announce Type: new
Abstract: Coupled gradient descent--where the update of one parameter block depends on another--underlies bilevel optimization, two-time-scale stochastic approximation, and adversarial training. When the coupled Jacobian is block-triangular, asymptotic stabilit...
Do Transformers Need Three Projections? Systematic Study of QKV Variants
arXiv:2606.04032v1 Announce Type: new
Abstract: Transformers have become the standard solution for various AI tasks, with the query, key, and value (QKV) attention formulation playing a central role. However, the individual contribution of these three projections and the impact of omitting some rem...
Spectral Asymptotics of Neural Network Loss Landscapes: An Exact Decomposition of the Curvature Exponent
arXiv:2606.02596v1 Announce Type: new
Abstract: The curvature exponent $\alpha$ in $h_k \propto \sigma_k^\alpha$ -- governing how Hessian eigenvalues scale with gradient singular values -- varies systematically across layer types ($\alpha \approx 2$ for convolutions, $\approx 1$ for transformer att...
arXiv:2606.02597v1 Announce Type: new
Abstract: The development of brain-computer interfaces (BCIs) based on electroencephalograms (EEGs) has advanced significantly mainly to machine learning. Although the majority of earlier research has been on increasing classification accuracy, relatively littl...
Assessing Region-Level EEG Contributions to Cognitive Workload Prediction
arXiv:2606.02598v1 Announce Type: new
Abstract: Accurate and generalizable estimation of cognitive workload from electroencephalography (EEG) is critical for human-centered and safety-critical systems. Although EEG is widely used for workload assessment, the consistency of region-level EEG contribu...
Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection
arXiv:2606.02601v1 Announce Type: new
Abstract: Within-dataset class-split evaluation is widely used as a proxy for fully unconditional out-of-distribution anomaly detection. We show that this protocol can become ill-posed when the held-out anomaly class overlaps the normal mixture in representatio...
BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization
arXiv:2606.00079v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-intensive because all expert weights must be kept resident in memory. Existing MoE compression methods st...