Harmonic Loss Trains Interpretable AI Models

Kavli Affiliate: Max Tegmark | Summary:In this paper, we introduce harmonic loss as an alternative supervisory signal for training neural networks and large language models (LLMs). Harmonic loss differs from standard cross-entropy loss by (a) replacing the usual SoftMax normalization with a scale-invariant HarMax function and (b) computing logits via Euclidean distance rather than a […]


Continue.. Harmonic Loss Trains Interpretable AI Models

Genetic Architecture and Analysis Practices of Circulating Metabolites in the NHLBI Trans-Omics for Precision Medicine (TOPMed) Program

Kavli Affiliate: V. S. Ramachandran | Authors: Nannan Wang, Franklin P. Ockerman, Laura Y. Zhou, Megan L Grove, Taryn Alkis, John Barnard, Russell P. Bowler, Clary B. Clish, Shinhye Chung, Emily Drzymalla, Anne M. Evans, Nora Franceschini, Robert E. Gerszten, Madeline G. Gillman, Scott R. Hutton, Rachel S. Kelly, Charles Kooperberg, Martin G. Larson, Jessica […]


Continue.. Genetic Architecture and Analysis Practices of Circulating Metabolites in the NHLBI Trans-Omics for Precision Medicine (TOPMed) Program

Two-particle quantum interference in a nonlinear optical medium: a witness of timelike indistinguishability

Kavli Affiliate: Jing Wang | First 5 Authors: Chao Chen, Shu-Tian Xue, Yu-Peng Shi, Jing Wang, Zi-Mo Cheng | Summary: The Hong-Ou-Mandel effect is a paradigmatic quantum phenomenon demonstrating the interference of two indistinguishable photons that are linearly coupled at a 50:50 beam splitter. Here, we transpose such a two-particle quantum interference effect to the […]


Continue.. Two-particle quantum interference in a nonlinear optical medium: a witness of timelike indistinguishability

Learning Fused State Representations for Control from Multi-View Observations

Kavli Affiliate: Li Xin Li | First 5 Authors: Zeyu Wang, Yao-Hui Li, Xin Li, Hongyu Zang, Romain Laroche | Summary: Multi-View Reinforcement Learning (MVRL) seeks to provide agents with multi-view observations, enabling them to perceive environment with greater effectiveness and precision. Recent advancements in MVRL focus on extracting latent representations from multiview observations and […]


Continue.. Learning Fused State Representations for Control from Multi-View Observations

Learning Fused State Representations for Control from Multi-View Observations

Kavli Affiliate: Li Xin Li | First 5 Authors: Zeyu Wang, Yao-Hui Li, Xin Li, Hongyu Zang, Romain Laroche | Summary: Multi-View Reinforcement Learning (MVRL) seeks to provide agents with multi-view observations, enabling them to perceive environment with greater effectiveness and precision. Recent advancements in MVRL focus on extracting latent representations from multiview observations and […]


Continue.. Learning Fused State Representations for Control from Multi-View Observations

Harnessing the Evolution of Proteostasis Networks to Reverse Cognitive Dysfunction

Kavli Affiliate: Yifan Cheng | Authors: Junrui Li, Yifei chen, Shawn Zheng, Angus McDonald, John W. Sedat, David A. Agard and Yifan Cheng | Summary: With technological advancements in recent years, single particle cryogenic electron microscopy (cryo-EM) has become a major methodology for structural biology. Structure determination by single particle cryo-EM is premised on randomly […]


Continue.. Harnessing the Evolution of Proteostasis Networks to Reverse Cognitive Dysfunction

Population Representation of the Confidence in a Decision in the Parietal Cortex

Kavli Affiliate: Michael Shadlen | Authors: Ariel Zylberberg and Michael N Shadlen | Summary: Confidence in a decision is the belief, prior to feedback, that one’s choice is correct. In the brain, many decisions are implemented as a race between competing evidence-accumulation processes. We ask whether the neurons that represent evidence accumulation also carry information […]


Continue.. Population Representation of the Confidence in a Decision in the Parietal Cortex

Psychometric-Based Evaluation for Theorem Proving with Large Language Models

Kavli Affiliate: Long Zhang | First 5 Authors: Jianyu Zhang, Yongwang Zhao, Long Zhang, Jilin Hu, Xiaokun Luan | Summary: Large language models (LLMs) for formal theorem proving have become a prominent research focus. At present, the proving ability of these LLMs is mainly evaluated through proof pass rates on datasets such as miniF2F. However, […]


Continue.. Psychometric-Based Evaluation for Theorem Proving with Large Language Models

LEAD: Large Foundation Model for EEG-Based Alzheimer’s Disease Detection

Kavli Affiliate: Xiang Zhang | First 5 Authors: Yihe Wang, Nan Huang, Nadia Mammone, Marco Cecchi, Xiang Zhang | Summary: Electroencephalogram (EEG) provides a non-invasive, highly accessible, and cost-effective solution for Alzheimer’s Disease (AD) detection. However, existing methods, whether based on manual feature extraction or deep learning, face two major challenges: the lack of large-scale […]


Continue.. LEAD: Large Foundation Model for EEG-Based Alzheimer’s Disease Detection

Evaluation of sequencing reads at scale using rdeval

Kavli Affiliate: Erich Jarvis | Authors: Giulio Formenti, Bonhwang Koo, Marco Sollitto, Jennifer Balacco, Nadolina Brajuka, Richard Burhans, Erick Duarte, Alice Maria Giani, Kirsty McCaffrey, Jack A Medico, Eugene W Myers and Erich D Jarvis | Summary: Motivation Large sequencing data sets are produced and deposited into public archives at unprecedented rates. The availability of […]


Continue.. Evaluation of sequencing reads at scale using rdeval