University of East Anglia
PulseAugur coverage of University of East Anglia — every cluster mentioning University of East Anglia across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AI assists mathematician in solving Riemann Hypothesis, human proof also emerges
A mathematician working at Anthropic, Levent Alpöge, has claimed a solution to the 167-year-old Riemann Hypothesis, a problem considered one of the most significant in mathematics. Alpöge utilized AI, specifically menti…
-
Time series foundation models show modest gains over random initialization
Two new research papers explore the effectiveness of foundation models for time series classification. The first paper questions the contribution of pre-trained weights, finding modest gains over randomly initialized mo…
-
TIDES model enhances irregular time series handling in selective SSMs
Researchers have introduced TIDES, a novel variant of selective state space models designed to improve handling of irregular time series data. Unlike existing selective SSMs like Mamba, which learn input-dependent time …
-
TIDES model advances irregular time series handling in state space models
Researchers have introduced TIDES, a novel selective state space model (SSM) designed to effectively handle irregular time series data. Unlike existing models like Mamba, which learn a step size that deviates from physi…
-
Progressive Memory Transformer enhances time-series analysis with multi-scale attention
Researchers have introduced the Progressive Memory Transformer (PMT), a novel architecture designed to enhance time-series analysis by explicitly leveraging hierarchical structures across multiple scales. Unlike existin…
-
New INSHAPE framework offers instance-level interpretability for time-series classification
Researchers have developed INSHAPE, a novel framework for interpretable time-series classification. Unlike previous methods that focus on population-level patterns, INSHAPE identifies discriminative temporal patterns sp…
-
New FreSH framework enhances multivariate time series classification
Researchers have developed FreSH, a novel framework for multivariate time series classification that addresses challenges like class imbalance and computational efficiency. FreSH employs a frequency-segmented, hierarchi…
-
New PDFTime framework boosts time series classification accuracy
Researchers have introduced PDFTime, a novel framework designed to enhance the accuracy and interpretability of multivariate time series classification. This approach moves away from direct feature-to-label mapping by e…
-
New INSHAPE framework offers interpretable time-series classification
Researchers have introduced INSHAPE, a novel framework for interpretable time-series classification. This method discovers variable-length temporal patterns specific to individual time series, modeling their dependencie…
-
LLM agents enable training-free time series classification via in-context reasoning
Researchers have developed FETA, a novel multi-agent framework designed for training-free time series classification using LLMs. This approach decomposes time series data into channel-specific problems, retrieves simila…