Related papers: A Conversation with Jon Wellner
Research in the field of Artificial Intelligence is continually progressing to simulate the human knowledge into automated intelligent knowledge base, which can encode and retrieve knowledge efficiently along with the capability of being is…
The career and accomplishments of Julian Schwinger, who shared the Nobel Prize for physics in 1965, have been reviewed in numerous books and articles. For this reason these Memories, which seek to convey a sense of Schwinger's remarkable…
This volume contains the proceedings of the Workshop on Partiality and Recursion in Interactive Theorem Provers (PAR 2010) which took place on July 15 in Edinburgh, UK. This workshop was held as a satellite workshop of the International…
From the 2016 U.S. presidential election to the 2021 Capitol riots to the spread of misinformation related to COVID-19, many have blamed social media for today's deeply divided society. Recent advances in machine learning for signed…
These are the notes for the lecture given by the author at the "Current Events" Special Session of the AMS meeting in Baltimore on January 17, 2003. Topics reviewed include the Langlands correspondence for GL(n) in the function field case…
A brief, personal, and very incomplete account of 50 years of pulsar astronomy presented at the Conference Dinner for "Physics of Neutron Stars - 2017 - 50 Years After", held in Saint Petersburg, July 2017.
We study an intermittent random walk on a random network of scale-free degree distribution. The walk is a combination of simple random walks of duration $t_w$ and random long-range jumps. While the time the walker needs to cover all the…
Named Entity Recognition (NER) in Few-Shot setting is imperative for entity tagging in low resource domains. Existing approaches only learn class-specific semantic features and intermediate representations from source domains. This affects…
Lightning strokes create powerful electromagnetic pulses that routinely cause very low frequency (VLF) waves to propagate across hemispheres along geomagnetic field lines. VLF antenna receivers can be used to detect these whistler waves…
The Circle of Willis (CoW) is a critical network of arteries in the brain, often implicated in cerebrovascular pathologies. Voxel-level segmentation is an important first step toward an automated CoW assessment, but a full quantitative…
This paper introduces a simple efficient learning algorithms for general sequential decision making. The algorithm combines Optimism for exploration with Maximum Likelihood Estimation for model estimation, which is thus named OMLE. We prove…
In this work, we revisit the problem of semi-supervised named entity recognition (NER) focusing on extremely light supervision, consisting of a lexicon containing only 10 examples per class. We introduce ELLEN, a simple, fully modular,…
Rigorous evaluation of large language models (LLMs) relies on comparing models by the prevalence of desirable or undesirable behaviors, such as task pass rates or policy violations. These prevalence estimates are produced by a classifier,…
With contemporary data sets becoming too large to analyze the data directly, various forms of aggregated data are becoming common. The original individual data are points, but after aggregation, the observations are interval-valued (e.g.).…
Vision-and-Language Navigation (VLN) is a natural language grounding task where agents have to interpret natural language instructions in the context of visual scenes in a dynamic environment to achieve prescribed navigation goals.…
A new bimodal generative model is proposed for generating conditional and joint samples, accompanied with a training method with learning a succinct bottleneck representation. The proposed model, dubbed as the variational Wyner model, is…
This contribution to the book in honour of J.S. Bell will probably differ from the remaining ones, in particular since only a part of it will be devoted to specific technical arguments. In fact I have considered appropriate to share with…
On January 4, 2012, the centenary of Henri Poincar\'e's death, a colloquium was held in Nancy, France the subject of which was "Vers une biographie d'Henri Poincar\'e". Scholars discussed several approaches for writing a biography of…
Despite significant recent progress, the best available computer vision algorithms still lag far behind human capabilities, even for recognizing individual discrete objects under various poses, illuminations, and backgrounds. Here we…
Reliable Large Language Models (LLMs) should abstain when confidence is insufficient. However, prior studies often treat refusal as a generic "I don't know'', failing to distinguish input-level ambiguity (data uncertainty) from capability…