3 papers
cs.LG2026
Model-agnostic Retrieval-Augmented Extended Forecasting for time series
Juan Pablo Villa Serna, Rohan Asthana, Vasileios Belagiannis
Time series forecasting with pretrained foundation models has demonstrated strong zero-shot capabilities. However, achieving optimal performance on time series with short or neglig…
cs.LG2026
Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability
Rohan Asthana, Vasileios Belagiannis
Diffusion-based image generative models produce high-fidelity images through iterative denoising but remain vulnerable to memorization, where they unintentionally reproduce exact c…
cs.CV2025
Dextr: Zero-Shot Neural Architecture Search with Singular Value Decomposition and Extrinsic Curvature
Rohan Asthana, Joschua Conrad, Maurits Ortmanns +1
Zero-shot Neural Architecture Search (NAS) typically optimises the architecture search process by exploiting the network or gradient properties at initialisation through zero-cost…