Prompt engineering is a technique that involves augmenting a large
pre-t...
Despite the rich literature on machine learning fairness, relatively lit...
Language models still struggle on moral reasoning, despite their impress...
Video self-supervised learning (VSSL) has made significant progress in r...
With the advent of vision-language models (VLMs) that can perform in-con...
As task-oriented dialog systems are becoming increasingly popular in our...
Recent neural models that extend the pretrain-then-finetune paradigm con...
We derive information-theoretic lower bounds on the Bayes risk and
gener...
Federated learning (FL) is an emerging privacy-preserving paradigm, wher...
While deep learning through empirical risk minimization (ERM) has succee...
Exponential tilting is a technique commonly used in fields such as
stati...
MultiWOZ is one of the most popular multi-domain task-oriented dialog
da...
In this paper, we propose a new notion of fairness violation, called
Exp...
A video-grounded dialogue system is required to understand both dialogue...
Models trained in machine learning processes may store information about...
In addition to accuracy, fairness and robustness are two critical concer...
This paper introduces the Ninth Dialog System Technology Challenge (DSTC...
Motivated by the needs of resource constrained dialog policy learning, w...
According to recent empirical studies, a majority of users have the same...
Empirical risk minimization (ERM) is typically designed to perform well ...
Competition is a primary driver of player satisfaction and engagement in...
Next generation virtual assistants are envisioned to handle multimodal i...
In many areas, massive amounts of data are collected and analyzed in ord...
We study the problem of mismatched guesswork, where we evaluate the numb...
In recent years, reinforcement learning has been successful in solving v...
There is a high demand for high-quality Non-Player Characters (NPCs) in ...
Recently, there have been several high-profile achievements of agents
le...
Recently, there have been several high-profile achievements of agents
le...
Packets originated from an information source in the network can be high...
We study a distributed learning problem in which Alice sends a compresse...
In September 2017, McAffee Labs quarterly report estimated that brute fo...
Given a collection of strings, each with an associated probability of
oc...
We consider an abstraction of computational security in password protect...
The randomized-feature approach has been successfully employed in large-...
We consider the parametric learning problem, where the objective of the
...
We present an information-theoretic framework for bounding the number of...