arXiv Machine Learning
Persistence Paradox in Dynamic Science: Evidence from the Deep Learning Revolution
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Sep 15
Has Scientific Talent Shifted from Depth to Breadth?Evidence across Papers, Knowledge Inputs, Careers, and Teams
arXiv:2609.14425v1 Announce Type: cross Abstract: Generative artificial intelligence raises a central question for scientific training and organization. Is research shifting from deep specialization...
arXiv AI
Oct 21
Stronger artificial intelligence breakthroughs hasten their own exhaustion
The paper argues that progress in AI is not simply a function of scale or the breadth of ideas, but depends on diverse attention, which can be depleted by collective focus on a single paradigm. Analyzing 36 years of computer‑science literature, the authors find that after the Transformer, the field’s attention narrowed sharply, with many researchers shifting into AI and reviewer confidence dropping. Each major breakthrough— from AlexNet to large language models—raises the field’s capacity for ideas but also accelerates the exhaustion of those ideas, a cycle mirrored in structural biology after cryo‑EM and AlphaFold. The study warns that policies like reciprocal reviewing may unintentionally concentrate attention on prolific authors, urging institutions to safeguard diverse attention rather than reward concentration on a single winning paradigm.
arXiv AI
Sep 25
AI in Science: Early Insights
The paper "AI in Science: Early Insights" analyzes AI’s impact on scientific work using data from 15 million Gemini interactions, 2,600 specialized AI models, and a survey of 600 scientists. It finds widespread AI adoption, complementary use of large language models and specialized tools, significant productivity gains of about seven hours per week, and a shift in research bottlenecks toward hypothesis backlog and verification needs. The study suggests AI can boost scientific productivity but its full effect depends on addressing new downstream challenges.
arXiv AI
Oct 16
Time to Fake It: Continual Machine Learning Intensifies Unfairness in Deepfake Detection
The paper examines how continual learning (CL) techniques used to update deepfake detectors over time affect fairness across different demographic groups. By training detectors on a chronological series of 11 real-world deepfake generation methods, the authors track four fairness dimensions and find that accuracy loss often worsens unfairness, while fairness gains are rare. The study reveals that inequitable forgetting is linked to representation learning rather than mere underrepresentation, urging CL methods to consider social outcomes when balancing stability and plasticity.
arXiv AI
Jun 16
An Empirical Investigation of Pre-Trained Deep Learning Model Reuse in the Scientific Process
arXiv:2603. 13584v2 Announce Type: replace-cross Abstract: Deep learning has achieved recognition for its impact within natural sciences, yet the prohibitive financial and technical cost of training models from scratch inhibit adoption.
arXiv Machine Learning
Jun 3
Forecasting Conceptual Diffusion in Science: The Case of Quantum Computing
arXiv:2606. 03919v1 Announce Type: cross Abstract: Understanding and anticipating scientific change requires models that distinguish between endogenous consolidation and exogenous diffusion of scientific concepts.