Tootfinder

⏰ New study challenges assumptions linking racial attitudes and political identity in U.S. cities
https://phys.org/news/2025-06-assumptions-linking-racial-attitudes-political.html

New study challenges assumptions linking racial attitudes and political identity in U.S. cities
Nearly 40% of U.S. cities analyzed in a study in NPJ Complexity diverge from the common narrative that Republican-dominated areas have high levels of implicit racial bias while Democratic strongholds are more tolerant.

VidFuncta: Towards Generalizable Neural Representations for Ultrasound Videos
Julia Wolleb, Florentin Bieder, Paul Friedrich, Hemant D. Tagare, Xenophon Papademetris
https://arxiv.org/abs/2507.21863

VidFuncta: Towards Generalizable Neural Representations for Ultrasound Videos
Ultrasound is widely used in clinical care, yet standard deep learning methods often struggle with full video analysis due to non-standardized acquisition and operator bias. We offer a new perspective on ultrasound video analysis through implicit neural representations (INRs). We build on Functa, an INR framework in which each image is represented by a modulation vector that conditions a shared neural network. However, its extension to the temporal domain of medical videos remains unexplored. T…

Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon
Tongtong Liang, Dan Qiao, Yu-Xiang Wang, Rahul Parhi
https://arxiv.org/abs/2506.20779

Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon
We study the implicit bias of flatness / low (loss) curvature and its effects on generalization in two-layer overparameterized ReLU networks with multivariate inputs -- a problem well motivated by the minima stability and edge-of-stability phenomena in gradient-descent training. Existing work either requires interpolation or focuses only on univariate inputs. This paper presents new and somewhat surprising theoretical results for multivariate inputs. On two natural settings (1) generalization g…

This https://arxiv.org/abs/2505.11370 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Understanding Nonlinear Implicit Bias via Region Counts in Input Space
One explanation for the strong generalization ability of neural networks is implicit bias. Yet, the definition and mechanism of implicit bias in non-linear contexts remains little understood. In this work, we propose to characterize implicit bias by the count of connected regions in the input space with the same predicted label. Compared with parameter-dependent metrics (e.g., norm or normalized margin), region count can be better adapted to nonlinear, overparameterized models, because it is de…

This https://arxiv.org/abs/2506.00253 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
Although value-aligned language models (LMs) appear unbiased in explicit bias evaluations, they often exhibit stereotypes in implicit word association tasks, raising concerns about their fair usage. We investigate the mechanisms behind this discrepancy and find that alignment surprisingly amplifies implicit bias in model outputs. Specifically, we show that aligned LMs, unlike their unaligned counterparts, overlook racial concepts in early internal representations when the context is ambiguous. …

High-Frequency First: A Two-Stage Approach for Improving Image INR
Sumit Kumar Dam, Mrityunjoy Gain, Eui-Nam Huh, Choong Seon Hong
https://arxiv.org/abs/2508.15582 https://

High-Frequency First: A Two-Stage Approach for Improving Image INR
Implicit Neural Representations (INRs) have emerged as a powerful alternative to traditional pixel-based formats by modeling images as continuous functions over spatial coordinates. A key challenge, however, lies in the spectral bias of neural networks, which tend to favor low-frequency components while struggling to capture high-frequency (HF) details such as sharp edges and fine textures. While prior approaches have addressed this limitation through architectural modifications or specialized …

Simulation-Based Inference for Direction Reconstruction of Ultra-High-Energy Cosmic Rays with Radio Arrays
Oscar Macias, Zachary Mason, Matthew Ho, Ars\`ene Ferri\`ere, Aur\'elien Benoit-L\'evy, Mat\'ias Tueros
https://arxiv.org/abs/2508.15991

Simulation-Based Inference for Direction Reconstruction of Ultra-High-Energy Cosmic Rays with Radio Arrays
Ultra-high-energy cosmic-ray (UHECR) observatories require unbiased direction reconstruction to enable multi-messenger astronomy with sparse, nanosecond-scale radio pulses. Explicit likelihood methods often rely on simplified models, which may bias results and understate uncertainties. We introduce a simulation-based inference pipeline that couples a physics-informed graph neural network (GNN) to a normalizing-flow posterior within the \textit{Learning the Universe Implicit Likelihood Inference…

Correcting for Position Bias in Learning to Rank: A Control Function Approach
Md Aminul Islam, Kathryn Vasilaky, Elena Zheleva
https://arxiv.org/abs/2506.06989

Correcting for Position Bias in Learning to Rank: A Control Function Approach
Implicit feedback data, such as user clicks, is commonly used in learning-to-rank (LTR) systems because it is easy to collect and it often reflects user preferences. However, this data is prone to various biases, and training an LTR system directly on biased data can result in suboptimal ranking performance. One of the most prominent and well-studied biases in implicit feedback data is position bias, which occurs because users are more likely to interact with higher-ranked documents regardless …

Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes
Shahed Masoudian, Gustavo Escobedo, Hannah Strauss, Markus Schedl
https://arxiv.org/abs/2508.03292

Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes
As Large Language Models (LLMs) are increasingly used across different applications, concerns about their potential to amplify gender biases in various tasks are rising. Prior research has often probed gender bias using explicit gender cues as counterfactual, or studied them in sentence completion and short question answering tasks. These formats might overlook more implicit forms of bias embedded in generative behavior of longer content. In this work, we investigate gender bias in LLMs using g…

Random-effects meta-analysis via generalized linear mixed models: A Bartlett-corrected approach for few studies
Keisuke Hanada, Tomoyuki Sugimoto
https://arxiv.org/abs/2508.08758

Random-effects meta-analysis via generalized linear mixed models: A Bartlett-corrected approach for few studies
Random-effects meta-analysis is widely used for synthesizing results across studies, but the implicit assumption of normality in study-specific aggregate data is often violated. Such violations can lead to biased estimates and misleading conclusions, especially in meta-analyses with small studies or rare events. A prominent example occurs with the log-odds ratio, which exhibits bias that depends on the within-study sample sizes. We first show that conventional methods assuming normality fail to…

Intrinsic training dynamics of deep neural networks
Sibylle Marcotte, Gabriel Peyr\'e, R\'emi Gribonval
https://arxiv.org/abs/2508.07370 https://ar…

Intrinsic training dynamics of deep neural networks
A fundamental challenge in the theory of deep learning is to understand whether gradient-based training in high-dimensional parameter spaces can be captured by simpler, lower-dimensional structures, leading to so-called implicit bias. As a stepping stone, we study when a gradient flow on a high-dimensional variable $θ$ implies an intrinsic gradient flow on a lower-dimensional variable $z = ϕ(θ)$, for an architecture-related function $ϕ$. We express a so-called intrinsic dynamic property and…

Synergizing Implicit and Explicit User Interests: A Multi-Embedding Retrieval Framework at Pinterest
Zhibo Fan, Hongtao Lin, Haoyu Chen, Bowen Deng, Hedi Xia, Yuke Yan, James Li
https://arxiv.org/abs/2506.23060

Synergizing Implicit and Explicit User Interests: A Multi-Embedding Retrieval Framework at Pinterest
Industrial recommendation systems are typically composed of multiple stages, including retrieval, ranking, and blending. The retrieval stage plays a critical role in generating a high-recall set of candidate items that covers a wide range of diverse user interests. Effectively covering the diverse and long-tail user interests within this stage poses a significant challenge: traditional two-tower models struggle in this regard due to limited user-item feature interaction and often bias towards t…

This https://arxiv.org/abs/2505.14449 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach
While subgroup disparities and performance bias are increasingly studied in computational research, fairness in categorical Speech Emotion Recognition (SER) remains underexplored. Existing methods often rely on explicit demographic labels, which are difficult to obtain due to privacy concerns. To address this limitation, we introduce an Implicit Demography Inference (IDI) module that leverages pseudo-labeling from a pre-trained model and unsupervised learning using k-means clustering to mitigat…