79 papers
This paper argues that the interaction between vulnerable individuals with mental health conditions and AI chatbots creates dangerous feedback loops—driven by human cognitive biases and AI sycophancy—that can destabilize beliefs and foster dependence, necessitating urgent coordinated action across clinical, developmental, and regulatory domains to mitigate emerging public health risks.
The paper introduces pHapCompass, a probabilistic algorithm for assembling and quantifying uncertainty in polyploid haplotypes that addresses read assignment ambiguity through graph-theoretic inference, while also providing a realistic simulation workflow and generalized evaluation metrics to demonstrate its competitive performance against existing assemblers.
This paper introduces MIG-Vis, a method combining variational autoencoders with mutual information-guided diffusion models to directly visualize and validate that neural populations in the macaque inferior temporal cortex are organized into structured, semantically meaningful latent groups encoding specific visual features like object pose and category transformations.
This study utilizes long-term monitoring data from three Guangdong reservoirs to develop a dynamic multi-factor hydro-ecological model that reveals total nitrogen as a more influential driver than total phosphorus for chlorophyll-a proliferation and quantifies the synergistic enhancement of algal growth when water temperatures exceed 25°C alongside high nitrogen levels.
This paper proposes a phase-field framework for simulating intrinsic and extrinsic apoptotic cell death driven by an activation field, which successfully reproduces key morphological transitions like shrinkage and fragmentation while offering a potential tool for computational therapeutic testing.
This paper presents a data-driven quantitative model, calibrated with U.S. spillover data, to assess the weekly probability and spatiotemporal distribution of highly pathogenic avian influenza (H5N1) transmission from wild birds to Danish cattle, identifying coastal and border regions as high-risk areas primarily during winter months to guide targeted surveillance and preparedness.
This study demonstrates that a cross-species transfer learning approach, utilizing an attention-based BiLSTM model pretrained on mouse Patch-seq data and fine-tuned on human data, successfully improves the prediction of conserved GABAergic interneuron subclasses from electrophysiological recordings to transcriptomic identities.
This paper presents a quantitative theory explaining how the spherical cell body of "eyeless" *Chlamydomonas* mutants acts as a lens to create internal caustics, causing a phototaxis sign reversal because the flagellar response is dominated by the rapidly varying lensed signal rather than the direct illumination.
This paper introduces a parameter-efficient Diffusion Transformer (DiT) with a 2D CNN encoder that generates high-quality, cell-type-specific synthetic regulatory DNA sequences with significantly faster convergence, reduced memorization, and enhanced regulatory activity compared to existing U-Net-based models.
SNPgen is a two-stage conditional latent diffusion framework that generates privacy-preserving, phenotype-aligned synthetic genotype data, enabling machine learning models trained on synthetic samples to achieve predictive performance comparable to those trained on real data while maintaining strict privacy guarantees and preserving key genetic structures.
LabConstrictor is a GitHub-based automation tool that streamlines the deployment of Jupyter notebooks into one-click, installable desktop applications, thereby overcoming common barriers to software adoption and reproducibility in life sciences research.
This paper introduces a flexible stochastic beam search sampling method for masked language models that optimizes protein properties by evaluating entire-sequence neighborhoods, demonstrating through extensive in silico and in vitro antibody engineering experiments that the choice of sampling strategy is at least as critical as the model itself.
This paper introduces a novel three-stage mechanistic interpretability method that extracts a compact, high-performing hematopoietic algorithm directly from the internal attention weights of the scGPT foundation model, achieving superior zero-shot classification and pseudotime ordering on independent datasets with significantly fewer parameters and training time than standard probing or retraining approaches.
This paper introduces Equivariant Asynchronous Diffusion (EAD), a novel model that combines the strengths of auto-regressive and synchronous approaches through an adaptive denoising schedule to effectively capture molecular hierarchy and achieve state-of-the-art 3D molecular conformation generation.
This paper demonstrates that Restricted Boltzmann Machines can effectively model large-scale neural activity from approximately 1,500 to 2,000 simultaneously recorded neurons, capturing complex higher-order statistics and revealing anatomically structured interaction networks that align with visual behavior and global dynamics.
This paper presents a statistical-mechanical theory linking the linear decoding efficiency of continuous variables to the geometric properties of neural manifolds, revealing increasing decoding capacity for object position and size along the monkey visual stream.
This paper introduces a stochastic model demonstrating that while extreme value statistics of first-passage times allow a larger population to overcome a spatial disadvantage, a non-reciprocal interaction bias is strictly required to stabilize this transient superiority into macroscopic dominance.
This study employs a thermodynamically consistent reaction-diffusion framework to demonstrate that intracellular ATP levels and phosphorylation free energy act as critical regulators of trigger-wave speed, propagation direction, and the minimum critical nucleus size required for sustained spatial signaling in cellular biochemical systems.
The paper introduces JEDI, a hierarchical model that jointly learns shared embeddings over recurrent neural network weights to robustly infer generalizable, task-specific neural dynamics from noisy, high-dimensional experimental recordings, successfully recovering underlying mechanistic structures and providing insights into motor control.
This study of over 14,000 U.S. young adults reveals that while the modular community structure of mental health symptoms remained stable throughout the COVID-19 pandemic, the control within these networks shifted from a stress-centered configuration to a more distributed pattern across emotional, cognitive, and social domains.