Search Results for author:
Found 80 papers, 36 papers with code
VeTraSS: Vehicle Trajectory Similarity Search Through Graph Modeling and Representation Learning
Trajectory similarity search plays an essential role in autonomous driving, as it enables vehicles to analyze the information and characteristics of different trajectories to make informed decisions and navigate safely in dynamic environments.
On Uncertainty Quantification for Near-Bayes Optimal Algorithms
Bayesian modelling allows for the quantification of predictive uncertainty which is crucial in safety-critical applications.
PROC2PDDL: Open-Domain Planning Representations from Texts
Planning in a text-based environment continues to be a major challenge for AI systems.
ChatMusician: Understanding and Generating Music Intrinsically with LLM
It is based on continual pre-training and finetuning LLaMA2 on a text-compatible music representation, ABC notation, and the music is treated as a second language.
Differential Private Federated Transfer Learning for Mental Health Monitoring in Everyday Settings: A Case Study on Stress Detection
Mental health conditions, prevalent across various demographics, necessitate efficient monitoring to mitigate their adverse impacts on life quality.
Generalizable Visual Reinforcement Learning with Segment Anything Model
Learning policies that can generalize to unseen environments is a fundamental challenge in visual reinforcement learning (RL).
MVHuman: Tailoring 2D Diffusion with Multi-view Sampling For Realistic 3D Human Generation
Recent months have witnessed rapid progress in 3D generation based on diffusion models.
Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement
It first distills the videos into still images as static memory and then compensates the dynamic and motion information with a learnable dynamic memory block.
RigLSTM: Recurrent Independent Grid LSTM for Generalizable Sequence Learning
Sequential processes in real-world often carry a combination of simple subsystems that interact with each other in certain forms.
Distill Gold from Massive Ores: Efficient Dataset Distillation via Critical Samples Selection
Our method consistently enhances the distillation algorithms, even on much larger-scale and more heterogeneous datasets, e. g. ImageNet-1K and Kinetics-400.
HUB: Guiding Learned Optimizers with Continuous Prompt Tuning
By incorporating hand-designed optimizers as the second component in our hybrid approach, we are able to retain the benefits of learned optimizers while stabilizing the training process and, more importantly, improving testing performance.
Bulk-Switching Memristor-based Compute-In-Memory Module for Deep Neural Network Training
The efficacy of training larger models is evaluated using realistic hardware parameters and shows that that analog CIM modules can enable efficient mix-precision DNN training with accuracy comparable to full-precision software trained models.
PowerGAN: A Machine Learning Approach for Power Side-Channel Attack on Compute-in-Memory Accelerators
Analog compute-in-memory (CIM) systems are promising for deep neural network (DNN) inference acceleration due to their energy efficiency and high throughput.
Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos
The success of the Neural Radiance Fields (NeRFs) for modeling and free-view rendering static objects has inspired numerous attempts on dynamic scenes.
RN-Net: Reservoir Nodes-Enabled Neuromorphic Vision Sensing Network
Event-based cameras are inspired by the sparse and asynchronous spike representation of the biological visual system.
NoiseCAM: Explainable AI for the Boundary Between Noise and Adversarial Attacks
Our work could provide a useful tool to defend against certain adversarial attacks on deep neural networks.
Object-centric Learning with Cyclic Walks between Parts and Whole
To capture compositional entities of the scene, we proposed cyclic walks between perceptual features extracted from vision transformers and object entities.
HumanGen: Generating Human Radiance Fields with Explicit Priors
With the aid of the anchor image, we adapt a 3D reconstructor for fine-grained details synthesis and propose a two-stage blending scheme to boost appearance generation.
Zebra: Deeply Integrating System-Level Provenance Search and Tracking for Efficient Attack Investigation
System auditing has emerged as a key approach for monitoring system call events and investigating sophisticated attacks.
Spectral Representation Learning for Conditional Moment Models
For nonparametric conditional moment models, efficient estimation often relies on preimposed conditions on various measures of ill-posedness of the hypothesis space, which are hard to validate when flexible models are used.
Application of Deep Q Learning with Simulation Results for Elevator Optimization
This paper presents a methodology for combining programming and mathematics to optimize elevator wait times.
Modeling Perceptual Loudness of Piano Tone: Theory and Applications
The relationship between perceptual loudness and physical attributes of sound is an important subject in both computer music and psychoacoustics.
Generative Deformable Radiance Fields for Disentangled Image Synthesis of Topology-Varying Objects
Experiments show that our method can successfully learn the generative model from unstructured monocular images and well disentangle the shape and appearance for objects (e. g., chairs) with large topological variance.
SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization
Matching-based methods, especially those based on space-time memory, are significantly ahead of other solutions in semi-supervised video object segmentation (VOS).
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
Fast Instrument Learning with Faster Rates
We investigate nonlinear instrumental variable (IV) regression given high-dimensional instruments.
NeReF: Neural Refractive Field for Fluid Surface Reconstruction and Implicit Representation
We present a novel neural refractive field(NeReF) to recover wavefront of transparent fluids by simultaneously estimating the surface position and normal of the fluid front.
Kubric: A scalable dataset generator
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details.
DynaMixer: A Vision MLP Architecture with Dynamic Mixing
In contrast with vision transformers and CNNs, the success of MLP-like models shows that simple information fusion operations among tokens and channels can yield a good representation power for deep recognition models.
Audio-to-symbolic Arrangement via Cross-modal Music Representation Learning
This is the audio-to-symbolic arrangement problem we tackle in this paper.
C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
Although compressive sensing (CS) can be adopted to compress the signals to reduce communication bandwidth requirement, it needs a complex reconstruction procedure before the signal can be used for seizure prediction.
iButter: Neural Interactive Bullet Time Generator for Human Free-viewpoint Rendering
To fill this gap, in this paper we propose a neural interactive bullet-time generator (iButter) for photo-realistic human free-viewpoint rendering from dense RGB streams, which enables flexible and interactive design for human bullet-time visual effects.
Quasi-Bayesian Dual Instrumental Variable Regression
Recent years have witnessed an upsurge of interest in employing flexible machine learning models for instrumental variable (IV) regression, but the development of uncertainty quantification methodology is still lacking.
Scalable Quasi-Bayesian Inference for Instrumental Variable Regression
Recent years have witnessed an upsurge of interest in employing flexible machine learning models for instrumental variable (IV) regression, but the development of uncertainty quantification methodology is still lacking.
A Novel Multi-scale Dilated 3D CNN for Epileptic Seizure Prediction
Accurate prediction of epileptic seizures allows patients to take preventive measures in advance to avoid possible injuries.
Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization
This modeling choice assumes that different dimensions of the next state and reward are conditionally independent given the current state and action and may be driven by the fact that fully observable physics-based simulation environments entail deterministic transition dynamics.
MirrorNeRF: One-shot Neural Portrait Radiance Field from Multi-mirror Catadioptric Imaging
In this paper, we propose MirrorNeRF - a one-shot neural portrait free-viewpoint rendering approach using a catadioptric imaging system with multiple sphere mirrors and a single high-resolution digital camera, which is the first to combine neural radiance field with catadioptric imaging so as to enable one-shot photo-realistic human portrait reconstruction and rendering, in a low-cost and casual capture setting.
Benchmarks for Deep Off-Policy Evaluation
Off-policy evaluation (OPE) holds the promise of being able to leverage large, offline datasets for both evaluating and selecting complex policies for decision making.
Regularized Behavior Value Estimation
Due to bootstrapping, these errors get amplified during training and can lead to divergence, thereby crippling learning.
Addressing Extrapolation Error in Deep Offline Reinforcement Learning
These errors can be compounded by bootstrapping when the function approximator overestimates, leading the value function to *grow unbounded*, thereby crippling learning.
Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
Cycle-consistent training is widely used for jointly learning a forward and inverse mapping between two domains of interest without the cumbersome requirement of collecting matched pairs within each domain.
RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
Offline Learning from Demonstrations and Unlabeled Experience
Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations.
Further Analysis of Outlier Detection with Deep Generative Models
The recent, counter-intuitive discovery that deep generative models (DGMs) can frequently assign a higher likelihood to outliers has implications for both outlier detection applications as well as our overall understanding of generative modeling.
Learning Interpretable Representation for Controllable Polyphonic Music Generation
While deep generative models have become the leading methods for algorithmic composition, it remains a challenging problem to control the generation process because the latent variables of most deep-learning models lack good interpretability.
PIANOTREE VAE: Structured Representation Learning for Polyphonic Music
The dominant approach for music representation learning involves the deep unsupervised model family variational autoencoder (VAE).
POP909: A Pop-song Dataset for Music Arrangement Generation
The main body of the dataset contains the vocal melody, the lead instrument melody, and the piano accompaniment for each song in MIDI format, which are aligned to the original audio files.
Hyperparameter Selection for Offline Reinforcement Learning
Therefore, in this work, we focus on \textit{offline hyperparameter selection}, i. e. methods for choosing the best policy from a set of many policies trained using different hyperparameters, given only logged data.
Critic Regularized Regression
Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction.
RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
Acme: A Research Framework for Distributed Reinforcement Learning
These implementations serve both as a validation of our design decisions as well as an important contribution to reproducibility in RL research.
A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models
Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative.
Incentive Analysis of Bitcoin-NG, Revisited
First, we propose a new incentive analysis that takes the network capacity into account, showing that Bitcoin-NG can still maintain incentive compatibility against the microblock mining attack even under limited network capacity.
Cryptography and Security Distributed, Parallel, and Cluster Computing
The Usual Suspects? Reassessing Blame for VAE Posterior Collapse
In narrow asymptotic settings Gaussian VAE models of continuous data have been shown to possess global optima aligned with ground-truth distributions.
Task-Relevant Adversarial Imitation Learning
We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels.
Scaling data-driven robotics with reward sketching and batch reinforcement learning
We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions.
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial conditions.
Deep Music Analogy Via Latent Representation Disentanglement
Analogy-making is a key method for computer algorithms to generate both natural and creative music pieces.
Visual Imitation with a Minimal Adversary
The proposed agent can solve a challenging robot manipulation task of block stacking from only video demonstrations and sparse reward, in which the non-imitating agents fail to learn completely.
Function Space Particle Optimization for Bayesian Neural Networks
While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior inference remains challenging, due to the high-dimensional and over-parameterized nature.
A Framework for Automated Pop-song Melody Generation with Piano Accompaniment Arrangement
Second, the melody generation model generates the lead melody and other voices (melody lines) of the accompaniment using seasonal ARMA (Autoregressive Moving Average) processes.
Bayesian Optimization in AlphaGo
During the development of AlphaGo, its many hyper-parameters were tuned with Bayesian optimization multiple times.
One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL
MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators.
Playing hard exploration games by watching YouTube
One successful method of guiding exploration in these domains is to imitate trajectories provided by a human demonstrator.
Reinforcement and Imitation Learning for Diverse Visuomotor Skills
We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent.
Learning an Embedding Space for Transferable Robot Skills
We present a method for reinforcement learning of closely related skills that are parameterized via a skill embedding space.
The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously
This paper introduces the Intentional Unintentional (IU) agent.
Robust Imitation of Diverse Behaviors
Compared to purely supervised methods, Generative Adversarial Imitation Learning (GAIL) can learn more robust controllers from fewer demonstrations, but is inherently mode-seeking and more difficult to train.
Emergence of Locomotion Behaviours in Rich Environments
The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals.
Learning human behaviors from motion capture by adversarial imitation
Rapid progress in deep reinforcement learning has made it increasingly feasible to train controllers for high-dimensional humanoid bodies.
Parallel Multiscale Autoregressive Density Estimation
Our new PixelCNN model achieves competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical generation of 512x512 images.
Ranked #2 on
Image Compression
on ImageNet32
Sample Efficient Actor-Critic with Experience Replay
This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems.
Dueling Network Architectures for Deep Reinforcement Learning
In recent years there have been many successes of using deep representations in reinforcement learning.
Ranked #1 on
Atari Games
on Atari 2600 Pong
Deep Fried Convnets
The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters.
Ranked #54 on
Image Classification
on MNIST
Bayesian Optimisation for Machine Translation
This paper presents novel Bayesian optimisation algorithms for minimum error rate training of statistical machine translation systems.
Heteroscedastic Treed Bayesian Optimisation
At the core of this approach is a Gaussian process prior that captures our belief about the distribution over functions.
Theoretical Analysis of Bayesian Optimisation with Unknown Gaussian Process Hyper-Parameters
Bayesian optimisation has gained great popularity as a tool for optimising the parameters of machine learning algorithms and models.
An Entropy Search Portfolio for Bayesian Optimization
How- ever, the performance of a Bayesian optimization method very much depends on its exploration strategy, i. e. the choice of acquisition function, and it is not clear a priori which choice will result in superior performance.
Bayesian Multi-Scale Optimistic Optimization
In this paper, we introduce a new technique for efficient global optimization that combines Gaussian process confidence bounds and treed simultaneous optimistic optimization to eliminate the need for auxiliary optimization of acquisition functions.
Bayesian Optimization in a Billion Dimensions via Random Embeddings
Bayesian optimization techniques have been successfully applied to robotics, planning, sensor placement, recommendation, advertising, intelligent user interfaces and automatic algorithm configuration.
