Search Results for author:
Found 17 papers, 3 papers with code
PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play
To make diffusion models more useful for skill learning, we encourage robotic agents to acquire a vocabulary of skills by introducing discrete bottlenecks into the conditional behavior generation process.
Accelerating Graph Neural Networks via Edge Pruning for Power Allocation in Wireless Networks
Since unpaired transmitters and receivers are often spatially distant, the distanced-based threshold is proposed to reduce the computation time by excluding or including the channel state information in GNNs.
Affordances from Human Videos as a Versatile Representation for Robotics
Utilizing internet videos of human behavior, we train a visual affordance model that estimates where and how in the scene a human is likely to interact.
Graph Neural Networks for Power Allocation in Wireless Networks with Full Duplex Nodes
We further refine this trade-off by introducing a distance-based threshold for inclusion or exclusion of edges in the network.
SVoice: Enabling Voice Communication in Silence via Acoustic Sensing on Commodity Devices
The design of introduces a new model that provides the unique mapping relationship between ultrasound and speech signals, so that the audible speech can be successfully reconstructed from the silent speech.
Towards Correlated Sequential Rules
To compensate for this deficiency, high-utility sequential rule mining (HUSRM) is designed to explore the confidence or probability of predicting the occurrence of consequence sequential patterns based on the appearance of premise sequential patterns.
Anomaly Rule Detection in Sequence Data
Analyzing sequence data usually leads to the discovery of interesting patterns and then anomaly detection.
Flexible Pattern Discovery and Analysis
Based on the analysis of the proportion of utility in the supporting transactions used in the field of data mining, high utility-occupancy pattern mining (HUOPM) has recently attracted widespread attention.
MAF-GNN: Multi-adaptive Spatiotemporal-flow Graph Neural Network for Traffic Speed Forecasting
In this paper, we propose a Multi-adaptive Spatiotemporal-flow Graph Neural Network (MAF-GNN) for traffic speed forecasting.
Decision Transformer: Reinforcement Learning via Sequence Modeling
In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling.
Ranked #3 on
Offline RL
on D4RL
Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings
Recent advances in off-policy deep reinforcement learning (RL) have led to impressive success in complex tasks from visual observations.
Ranked #33 on
Atari Games
on Atari 2600 Amidar
State Entropy Maximization with Random Encoders for Efficient Exploration
Recent exploration methods have proven to be a recipe for improving sample-efficiency in deep reinforcement learning (RL).
Compute- and Memory-Efficient Reinforcement Learning with Latent Experience Replay
In this paper, we present Latent Vector Experience Replay (LeVER), a simple modification of existing off-policy RL methods, to address these computational and memory requirements without sacrificing the performance of RL agents.
Discovering High Utility-Occupancy Patterns from Uncertain Data
To find patterns that can represent the supporting transaction, a recent study was conducted to mine high utility-occupancy patterns whose contribution to the utility of the entire transaction is greater than a certain value.
Databases
SASO: Joint 3D Semantic-Instance Segmentation via Multi-scale Semantic Association and Salient Point Clustering Optimization
We propose a novel 3D point cloud segmentation framework named SASO, which jointly performs semantic and instance segmentation tasks.
Ranked #2 on
3D Instance Segmentation
on S3DIS
(mIoU metric)
3D Instance Segmentation
3D Semantic Instance Segmentation
+4
3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection
We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation.
Non-flat Ground Detection Based on A Local Descriptor
The main contribution of this paper is a newly proposed descriptor which is implemented in the disparity image to obtain a disparity texture image.
