In recent years, we have witnessed a surge of Graph Neural Networks (GNN...
Natural language provides a natural interface for human communication, y...
MuZero Unplugged presents a promising approach for offline policy learni...
Grounding spatial relations in natural language for object placing could...
Document-level relation extraction (RE) aims at extracting relations amo...
Graph Neural Networks (GNNs) have emerged as prominent models for
repres...
The traveling salesman problem is a fundamental combinatorial optimizati...
An inverse reinforcement learning (IRL) agent learns to act intelligentl...
A tree-based online search algorithm iteratively simulates trajectories ...
Ensemble and auxiliary tasks are both well known to improve the performa...
Manipulating deformable objects, such as cloth and ropes, is a long-stan...
Thompson sampling is a well-known approach for balancing exploration and...
Designing a network to learn a molecule structure given its physical/che...
Graph neural network models have been extensively used to learn node
rep...
Deep model-based reinforcement learning (MBRL) has achieved great
sample...
Graph Neural Networks (GNNs) tend to suffer performance degradation as m...
We propose a new sampling-based approach for approximate inference in
fi...
Deep reinforcement learning is successful in decision making for
sophist...
We address the problem of Visual Relationship Detection (VRD) which aims...
Aspect-based sentiment analysis produces a list of aspect terms and thei...
Most of the successful deep neural network architectures are structured,...
Recurrent neural networks (RNNs) have been extraordinarily successful fo...
Autonomous driving in a crowded environment, e.g., a busy traffic
inters...
This paper introduces the Differentiable Algorithm Network (DAN), a
comp...
Robot understanding of human intentions is essential for fluid human-rob...
We consider the cross-domain sentiment classification problem, where a
s...
We propose to take a novel approach to robot system design where each
bu...
Attention-based long short-term memory (LSTM) networks have proven to be...
This paper presents a planning system for autonomous driving among many
...
Driving among a dense crowd of pedestrians is a major challenge for
auto...
Particle filtering is a powerful method for sequential state estimation ...
Particle filters sequentially approximate posterior distributions by sam...
Human motion modeling is a classic problem in computer vision and graphi...
Planning under uncertainty is critical for robust robot performance in
u...
How can a delivery robot navigate reliably to a destination in a new off...
This paper introduces the QMDP-net, a neural network architecture for
pl...
Scarce data is a major challenge to scaling robot learning to truly comp...
The partially observable Markov decision process (POMDP) provides a
prin...
We study the robustness of active learning (AL) algorithms against prior...
The partially observable Markov decision process (POMDP) provides a
prin...
Bayesian reinforcement learning (BRL) encodes prior knowledge of the wor...