Beyond Vectors: A Smarter Way to Search High-Dimensional Data
A new indexing framework, CRISP, significantly accelerates approximate nearest neighbor search by intelligently partitioning data and optimizing for modern hardware.
Science
AI’s Easy Grade: Why Models Favor Their Own Work
![A model exhibits self-attribution bias by retrospectively undervaluing the risk associated with actions it has already performed, assigning a lower risk score to a completed action than when initially evaluating the same action in a hypothetical context-an effect amplified when the model both generates and assesses the risk of that action, demonstrating a form of post-hoc rationalization rather than consistent risk assessment-as if [latex]P(risk | action, model\_generated) < P(risk | action)[/latex].](https://arxiv.org/html/2603.04582v1/2603.04582v1/figures/figure1/figure1_final.png)
New research reveals that language models demonstrate a surprising bias, consistently rating their own outputs more favorably than those produced by others.
Convolutional Networks: How Built-In Constraints Shape Learning
A new analysis reveals how the core principles of convolutional neural networks – locality and weight sharing – fundamentally alter the way these models generalize and avoid overfitting.
Forecasting the Future: How Retrieval Can Boost Time-Series Prediction
A new framework leverages external knowledge to improve the accuracy of time-series forecasting, particularly in challenging industrial applications with limited data.
Taming the Complexity of Language Models
![The correlation function [latex]K(r)[/latex] of an additive Markov chain-constructed with a memory length of [latex]r=N=10[/latex] and parameters [latex]\overline{a}=1/2[/latex] and [latex]F_0=0.15[/latex]-demonstrates a correspondence between numerical solutions of equation (9) and calculations derived from the cumulative probability density function (7), revealing how memory embedded within the system’s dynamics shapes its overall correlation structure as defined by the memory function [latex]F(r)[/latex] (inset).](https://arxiv.org/html/2603.04412v1/2603.04412v1/x1.png)
New research connects the principles of statistical physics to the inner workings of large language models, offering a potential path to understanding-and mitigating-the challenges of high dimensionality.
Robots That Understand ‘Personal Space’: A New Approach to Safe Navigation
Researchers have developed a framework that allows robots to navigate complex social environments by factoring in semantic understanding and predicted human behavior.
Predicting the Unpredictable: AI Sharpening Wireless Channel Forecasts
A new framework leverages deep learning and Bayesian methods to improve the accuracy and reliability of wireless channel predictions, crucial for next-generation communication systems.
Subtle Sabotage: Crafting Hidden Attacks on Graph Neural Networks
Researchers have developed a new technique to subtly manipulate graph neural networks, creating backdoor vulnerabilities that are difficult to detect.
Buildings That Listen: Mapping Footsteps with Structural Vibration
![A building’s structure functions as a reservoir computer, localizing footsteps by converting the mechanical impulses of walking into dispersive vibrational fields sampled by implanted accelerometers, then projecting these signals-normalized and reduced via Principal Component Analysis-into reservoir state vectors used with trained weights to accurately estimate footstep location [latex] \hat{\mathbf{z}}\_{k}=(\hat{x}\_{k},\hat{y}\_{k}) [/latex].](https://arxiv.org/html/2603.04610v1/2603.04610v1/x1.png)
New research demonstrates that a building’s own structure can be harnessed as a sensor network to pinpoint footstep locations within its walls.
AI on the Stand: Can Algorithms Uncover Sentencing Bias?
A new study investigates whether artificial intelligence can help legal professionals build robust statistical evidence to support claims of racial disparities in sentencing.