We address catastrophic forgetting issues in graph learning as incoming ...
We present a new computing model for intrinsic rewards in reinforcement
...
The notion of shortcut partition, introduced recently by Chang, Conroy, ...
An essential requirement of spanners in many applications is to be
fault...
Recently the authors [CCLMST23] introduced the notion of shortcut partit...
While research on the geometry of planar graphs has been active in the p...
Code intelligence plays a key role in transforming modern software
engin...
Large language models (LLMs) pretrained on vast source code have achieve...
Large language models (LLMs) have significantly advanced the field of na...
We prove that there is a randomized polynomial-time algorithm that given...
A recent line of work on VC set systems in minor-free (undirected) graph...
In this paper we introduce BO-Muse, a new approach to human-AI teaming f...
Social reasoning necessitates the capacity of theory of mind (ToM), the
...
We introduce an approach for the answer-aware question generation proble...
Querying graph data with low latency is an important requirement in
appl...
The capacity to achieve out-of-distribution (OOD) generalization is a
ha...
Successful Artificial Intelligence systems often require numerous labele...
Data-free Knowledge Distillation (DFKD) has attracted attention recently...
We introduce LAVIS, an open-source deep learning library for LAnguage-VI...
Thorup [FOCS'01, JACM'04] and Klein [SODA'01] independently showed that ...
Program synthesis or code generation aims to generate a program that
sat...
Designed for tracking user goals in dialogues, a dialogue state tracker ...
We introduce OmniXAI, an open-source Python library of eXplainable AI (X...
Measuring the confidence of AI models is critical for safely deploying A...
We introduce a new constrained optimization method for policy gradient
r...
Machine learning of Theory of Mind (ToM) is essential to build social ag...
For summarization, human preference is critical to tame outputs of the
s...
Cohen-Addad, Filtser, Klein and Le [FOCS'20] constructed a stochastic
em...
Trojan attacks on deep neural networks are both dangerous and surreptiti...
In STOC'95 [ADMSS'95] Arya et al. showed that any set of n points in
ℝ^d...
We introduce a novel training procedure for policy gradient methods wher...
Seminal works on light spanners over the years provide spanners with opt...
Automatic summarization of legal texts is an important and still a
chall...
A (1+ϵ)-approximate distance oracle of an edge-weighted graph is a
data ...
Episodic control enables sample efficiency in reinforcement learning by
...
Sample-efficient generalisation of reinforcement learning approaches hav...
Let G = (V,E,w) be a weighted undirected graph on |V| = n vertices and
|...
Spanners for metric spaces have been extensively studied, both in genera...
Transfer in reinforcement learning is usually achieved through generalis...
The greedy spanner in a low dimensional Euclidean space is a fundamental...
Intelligence necessitates memory. Without memory, humans fail to perform...
Seminal works on light spanners over the years provide spanners with opt...
Video-grounded dialogue systems aim to integrate video understanding and...
Neural module networks (NMN) have achieved success in image-grounded tas...
Compared to traditional visual question answering, video-grounded dialog...
Chan, Har-Peled, and Jones [2020] recently developed locality-sensitive
...
In low distortion metric embeddings, the goal is to embed a host "hard"
...
A video-grounded dialogue system is required to understand both dialogue...
Video-grounded dialogues are very challenging due to (i) the complexity ...
Artificial Neural Networks are uniquely adroit at machine learning by
pr...