Science – Page 11

Seeing and Hearing is Believing? The Hunt for Audio-Visual Deepfakes

24.11.2025 by qfx

A comprehensive evaluation of self-supervised representations for audio-visual deepfake detection reveals their varying strengths in robustness and usefulness-assessed through linear probing and anomaly detection-as well as their interpretability via temporal and spatial explanations, and potential for synergistic improvement when combined through correlation and fusion analyses.

A new study comprehensively assesses how self-supervised learning can bolster the detection of increasingly realistic manipulated audio and video.

Seeing (and Hearing) is Believing: Detecting Deepfakes with AI

24.11.2025 by qfx

A comprehensive evaluation of self-supervised representations explores their efficacy in audio-visual deepfake detection, assessing not only their usefulness and resilience through linear probing and anomaly detection, but also dissecting their interpretability via temporal and spatial explanations and quantifying their synergistic potential through correlation and fusion analyses.

New research explores how artificial intelligence can leverage both audio and visual cues to identify increasingly realistic manipulated media.

Graph Networks Spot Network Threats with Speed and Precision

24.11.2025 by qfx

A new unsupervised learning approach leverages the power of graph autoencoders to detect anomalous network traffic with significantly improved performance.

Predictive Policing for Movement: New AI Flags Anomalous Trajectories

24.11.2025 by qfx

The CroTad framework establishes a cohesive system for task-oriented dialogue, integrating components to achieve comprehensive conversational understanding and response generation, and leveraging a structured approach to manage the complexities inherent in interactive exchanges.

A novel framework leverages contrastive learning and reinforcement learning to detect unusual patterns in movement data in real-time.

Spotting the Next Big Star: How TV and Twitter Predict Rising Talent

24.11.2025 by qfx

New research explores the power of combining social media buzz with television viewership to forecast emerging entertainment stars in Japan.

The Benchmark Blues: Why AI Evaluations Need a Second Look

24.11.2025 by qfx

The evaluation matrix details which large language models underwent testing across a suite of benchmarks, illuminating the specific combinations of model and assessment used in the study.

A new framework systematically identifies and corrects flawed questions within popular AI benchmarks, addressing a critical issue in reliable performance measurement.

Broken Data, Broken Algorithms: The Limits of Reinforcement Learning

24.11.2025 by qfx

New research highlights the critical impact of data integrity on the performance of reinforcement learning systems operating in complex, volatile environments.

Predicting the Road Ahead: Smarter Automotive Demand Forecasting

24.11.2025 by qfx

$(a)Life cycle patterns The study demonstrates that life cycle patterns, though diverse, frequently exhibit recurring phases of exponential growth followed by deceleration as resources become limited, a dynamic modeled by logistic equations such as $ \frac{dN}{dt} = rN(1 - \frac{N}{K}) $, where $r$ represents the intrinsic growth rate and $K$ the carrying capacity of the environment.$

A new approach to forecasting car sales leverages machine learning and data-driven insights to improve accuracy and optimize supply chain operations.

Beyond Whole Numbers: Neural Networks Tackle Fractional Growth

24.11.2025 by qfx

$Fractional exponential growth demonstrates that a quantity can increase at a rate proportional to a non-integer power of itself, offering a nuanced alternative to traditional exponential models where growth is governed by $e^x$ and instead allowing for rates described by functions like $e^{x^\alpha}$ with $0 < \alpha < 1$.$

A novel approach combines artificial neural networks with fractional calculus to more accurately model complex growth patterns.

Decoding Market Noise: Can Financial Data Generate true Randomness?

24.11.2025 by qfx

$The Hamming correlation, computed over sequences of length 32, demonstrates a quantifiable relationship between input patterns, effectively measuring their similarity through bitwise comparison-a fundamental operation in information theory encapsulated by the formula $H(x, y) = \sum_{i=0}^{L-1} (x_i \oplus y_i)$, where $L$ represents the sequence length and $\oplus$ denotes the exclusive OR operation.$

New research explores whether the inherent unpredictability of high-frequency financial markets can be harnessed to create statistically sound random number sequences.