We find limits to the Transformer architecture for language modeling and...
Efficient transfer learning algorithms are key to the success of foundat...
Discontinuities can be fairly arbitrary but also cause a significant imp...
Learning models that are robust to test-time distribution shifts is a ke...
We introduce equi-tuning, a novel fine-tuning method that transforms
(po...
It is crucial to successfully quantify causal effects of a policy
interv...
Recent work demonstrates a bias in the GPT-3 model towards generating vi...
Concrete is the most widely used engineered material in the world with m...
This work investigates functional source coding problems with maximal
di...
Humans can generalize from only a few examples and from little pre-train...
The Invariant Risk Minimization (IRM) framework aims to learn invariant
...
This paper presents a quantized Kalman filter implemented using unreliab...
The search for extraterrestrial intelligence (SETI) is a scientific ende...
Evaluating the inherent difficulty of a given data-driven classification...
Recent works show that including group equivariance as an inductive bias...
Conventional wireless techniques are becoming inadequate for beyond
fift...
Wireless power transfer (WPT) is an emerging paradigm that will enable u...
This paper studies the adversarial graphical contextual bandits, a varia...
Disparate access to resources by different subpopulations is a prevalent...
Many information sources are not just sequences of distinguishable symbo...
Human creativity is often described as the mental process of combining
a...
We consider reinforcement learning (RL) in episodic Markov decision proc...
Large-scale planting of trees has been proposed as a low-cost natural
so...
Recommender systems can influence human behavior in significant ways, in...
Neural text decoding is important for generating high-quality texts usin...
Transformer architectures have proven to learn useful representations fo...
We consider a strategic network quantizer design setting where agents mu...
Blockchain systems often employ proof-of-work consensus protocols to val...
Morphological inflection is a process of word formation where base words...
Interpretability of machine learning models has gained more and more
att...
Interests in the automatic generation of cooking recipes have been growi...
Some consider large-scale language models that can generate long and coh...
We study the problem of image registration in the finite-resolution regi...
We study a setting in which a principal selects an agent to execute a
co...
Consider a social learning problem in a parallel network, where N
distri...
Network flow is a powerful mathematical framework to systematically expl...
The "bee-identification problem" was formally defined by Tandon, Tan and...
We consider the problem of coding for computing with maximal distortion,...
Isometries and their induced symmetries are ubiquitous in the world. Tak...
Consumption of diets with low glycemic impact is highly recommended for
...
Cascading bandit (CB) is a variant of both the multi-armed bandit (MAB) ...
Large-scale language models show promising text generation capabilities,...
We present a principled framework to address resource allocation for
rea...
The paradigm of pretrained deep learning models has recently emerged in
...
We investigate the piecewise-stationary combinatorial semi-bandit proble...
Full-duplex communication allows a terminal to transmit and receive sign...
It is commonly observed that higher workload lowers job performance. We ...
Concrete is the most widely used engineered material in the world with m...
Consider the problem of identifying a massive number of bees, uniquely
l...
Deepfake detection is formulated as a hypothesis testing problem to clas...