Search Results for author:
Found 97 papers, 40 papers with code
Learning Sequence Attractors in Recurrent Networks with Hidden Neurons
We show that to store arbitrary pattern sequences, it is necessary for the network to include hidden neurons even though their role in displaying sequence memories is indirect.
Exploring the Impact of Dataset Bias on Dataset Distillation
Given that there are no suitable biased datasets for DD, we first construct two biased datasets, CMNIST-DD and CCIFAR10-DD, to establish a foundation for subsequent analysis.
AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents
We experimentally show that such "in-the-wild" data collected by AutoRT is significantly more diverse, and that AutoRT's use of LLMs allows for instruction following data collection robots that can align to human preferences.
Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge
Since models are typically quantized for edge deployment, recent work has investigated quantization-aware NAS (QA-NAS) to search for highly accurate and efficient quantized models.
Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native
In this paper, we investigate the intersection of large generative AI models and cloud-native computing architectures.
VILA: On Pre-training for Visual Language Models
Visual language models (VLMs) rapidly progressed with the recent success of large language models.
Ranked #21 on
Visual Question Answering
on MM-Vet
SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention
We present Self-Adaptive Robust Attention for Robotics Transformers (SARA-RT): a new paradigm for addressing the emerging challenge of scaling up Robotics Transformers (RT) for on-robot deployment.
Strings from the Library of Babel: Random Sampling as a Strong Baseline for Prompt Optimisation
Recent prompt optimisation approaches use the generative nature of language models to produce prompts -- even rivaling the performance of human-curated prompts.
AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages
Despite the recent progress on scaling multilingual machine translation (MT) to several under-resourced African languages, accurately measuring this progress remains challenging, since evaluation is often performed on n-gram matching metrics such as BLEU, which typically show a weaker correlation with human judgments.
RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches
Generalization remains one of the most important desiderata for robust robot learning systems.
RK-core: An Established Methodology for Exploring the Hierarchical Structure within Datasets
Across several benchmark datasets, we find that samples with low coreness values appear less representative of their respective categories, and conversely, those with high coreness values exhibit greater representativeness.
Can pre-trained models assist in dataset distillation?
Dataset Distillation (DD) is a prominent technique that encapsulates knowledge from a large-scale original dataset into a small synthetic dataset for efficient training.
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions
In this work, we present a scalable reinforcement learning method for training multi-task policies from large offline datasets that can leverage both human demonstrations and autonomously collected data.
Head-Tail Cooperative Learning Network for Unbiased Scene Graph Generation
We also propose a self-supervised learning approach to enhance the prediction ability of the tail-prefer feature representation branch by constraining tail-prefer predicate features.
Inferring gender from name: a large scale performance evaluation study
While inferring gender from name may raise some ethical questions, the lack of viable alternatives means that researchers have to resort to such approaches when the goal justifies the means - in the majority of such studies the goal is to examine patterns and determinants of gender disparities.
RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model
In this work, we propose an open-source benchmark named RTLLM, for generating design RTL with natural language instructions.
Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI
The Alexa Prize program has empowered numerous university students to explore, experiment, and showcase their talents in building conversational agents through challenges like the SocialBot Grand Challenge and the TaskBot Challenge.
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Our goal is to enable a single end-to-end trained model to both learn to map robot observations to actions and enjoy the benefits of large-scale pretraining on language and vision-language data from the web.
Joint adjustment image steganography networks
Thus, the security and quality of stego and revealed secret images still have much room for promotion, especially for large-capacity image steganography.
Event Detection from Social Media Stream: Methods, Datasets and Opportunities
Social media streams contain large and diverse amount of information, ranging from daily-life stories to the latest global and local events and news.
How does Contrastive Learning Organize Images?
Contrastive learning, a dominant self-supervised technique, emphasizes similarity in representations between augmentations of the same input and dissimilarity for different ones.
Spatiotemporal and Semantic Zero-inflated Urban Anomaly Prediction
Urban anomaly predictions, such as traffic accident prediction and crime prediction, are of vital importance to smart city security and maintenance.
SR-init: An interpretable layer pruning method
Our SR-init method is inspired by the discovery that the accuracy drop due to stochastic re-initialization of layer parameters differs in various layers.
Open-World Object Manipulation using Pre-trained Vision-Language Models
This brings up a notably difficult challenge for robots: while robot learning approaches allow robots to learn many different behaviors from first-hand experience, it is impractical for robots to have first-hand experiences that span all of this semantic information.
Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents
Recent progress in large language models (LLMs) has demonstrated the ability to learn and leverage Internet-scale knowledge through pre-training with autoregressive models.
Joint Optimization of Base Station Clustering and Service Caching in User-Centric MEC
To address single-base station (BS) transmission limitation and serious edge effect in traditional cellular-based edge service caching networks, in this paper, we proposed a novel user-centric edge service caching framework where each user is jointly provided with edge caching and wireless transmission services by a specific BS cluster instead of a single BS.
Deep adaptive hiding network for image hiding using attentive frequency extraction and gradual depth extraction
Image hiding secures information security in multimedia communication.
RT-1: Robotics Transformer for Real-World Control at Scale
By transferring knowledge from large, diverse, task-agnostic datasets, modern machine learning models can solve specific downstream tasks either zero-shot or with small task-specific datasets to a high level of performance.
Egocentric Hand-object Interaction Detection
In this paper, we propose a method to jointly determine the status of hand-object interaction.
Token Turing Machines
The model's memory module ensures that a new observation will only be processed with the contents of the memory (and not the entire history), meaning that it can efficiently process long sequences with a bounded computational cost at each step.
Ranked #1 on
Action Detection
on Charades
Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization
This problem is challenging, as it requires planning wiping actions while reasoning over uncertain latent dynamics of crumbs and spills captured via high-dimensional visual observations.
PI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale
The predictive information, the mutual information between the past and future, has been shown to be a useful representation learning auxiliary loss for training reinforcement learning agents, as the ability to model what will happen next is critical to success on many control tasks.
Low Error-Rate Approximate Multiplier Design for DNNs with Hardware-Driven Co-Optimization
In this paper, two approximate 3*3 multipliers are proposed and the synthesis results of the ASAP-7nm process library justify that they can reduce the area by 31. 38% and 36. 17%, and the power consumption by 36. 73% and 35. 66% compared with the exact multiplier, respectively.
AIA: Attention in Attention Within Collaborate Domains
Attention mechanisms can effectively improve the performance of the mobile networks with a limited computational complexity cost.
Alexa, Let's Work Together: Introducing the First Alexa Prize TaskBot Challenge on Conversational Task Assistance
Since its inception in 2016, the Alexa Prize program has enabled hundreds of university students to explore and compete to develop conversational agents through the SocialBot Grand Challenge.
The least-used key selection method for information retrieval in large-scale Cloud-based service repositories
The experimental results show that the proposed least-used key selection method improves the service retrieval efficiency significantly compared with the designated key selection method in the case of the unequal appearing probability of parameters in service retrieval requests under three indexing models.
Efficient Harmonic Neural Networks with Compound Discrete Cosine Transform filters and Shared Reconstruction filters
First, the spectrum feature learned by HNN is insufficient and limited because the number of DCT filters is much smaller than that of feature maps.
SeeFar: Vehicle Speed Estimation and Flow Analysis from a Moving UAV
In this paper, we introduce SeeFar to achieve vehicle speed estimation and traffic flow analysis based on YOLOv5 and DeepSORT from a moving drone.
Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures
With the advent of ubiquitous deployment of smart devices and the Internet of Things, data sources for machine learning inference have increasingly moved to the edge of the network.
Jump-Start Reinforcement Learning
In addition, we provide an upper bound on the sample complexity of JSRL and show that with the help of a guide-policy, one can improve the sample complexity for non-optimism exploration methods from exponential in horizon to polynomial.
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
We show how low-level skills can be combined with large language models so that the language model provides high-level knowledge about the procedures for performing complex and temporally-extended instructions, while value functions associated with these skills provide the grounding necessary to connect this knowledge to a particular physical environment.
On-Sensor Binarized Fully Convolutional Neural Network with A Pixel Processor Array
This work presents a method to implement fully convolutional neural networks (FCNs) on Pixel Processor Array (PPA) sensors, and demonstrates coarse segmentation and object localisation tasks.
HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks
We propose an optimization method for the automatic design of approximate multipliers, which minimizes the average error according to the operand distributions.
Detail-Preserving Transformer for Light Field Image Super-Resolution
DPT consists of two branches, with each associated with a Transformer for learning from an original or gradient image sequence.
Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning
Federated Learning is an emerging direction in distributed machine learning that en-ables jointly training a model without sharing the data.
Understanding the Dynamics of DNNs Using Graph Modularity
Specifically, we model the process of class separation of intermediate representations in pre-trained DNNs as the evolution of communities in dynamic graphs.
Graph-Based Similarity of Neural Network Representations
Understanding the black-box representations in Deep Neural Networks (DNN) is an essential problem in deep learning.
Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
Hierarchical reinforcement learning aims to enable this by providing a bank of low-level skills as action abstractions.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
RGP: Neural Network Pruning through Its Regular Graph Structure
In this paper, we study the graph structure of the neural network, and propose regular graph based pruning (RGP) to perform a one-shot neural network pruning.
Understanding Egocentric Hand-Object Interactions from Hand Pose Estimation
To show the ability to preserve the semantic information of our method, we also report the performance of grasp type classification on GUN-71 dataset and outperforms the benchmark by only using the predicted 3-d hand pose.
Egocentric Hand-object Interaction Detection and Application
We compare our method with the most recent work from Shan et al. \cite{Shan20} on selected images from EPIC-KITCHENS \cite{damen2018scaling} dataset and achieve $89\%$ accuracy on HOI (hand-object interaction) detection which is comparative to Shan's ($92\%$).
The Object at Hand: Automated Editing for Mixed Reality Video Guidance from Hand-Object Interactions
In this paper, we concern with the problem of how to automatically extract the steps that compose real-life hand activities.
Deep 3D-CNN for Depression Diagnosis with Facial Video Recording of Self-Rating Depression Scale Questionnaire
The superior performance of our system shows the validity of combining facial video recording with the SDS score for more accurate self-diagnose.
S2Looking: A Satellite Side-Looking Dataset for Building Change Detection
This paper therefore introduces S2Looking, a building-change-detection dataset that contains large-scale side-looking satellite images captured at various off-nadir angles.
Interpreting Depression From Question-wise Long-term Video Recording of SDS Evaluation
To automatically interpret depression from the SDS evaluation and the paired video, we propose an end-to-end hierarchical framework for the long-term variable-length video, which is also conditioned on the questionnaire results and the answering time.
Adversarial Sample Detection via Channel Pruning
Experiments on CIFAR10 and SVHN show that the FLOPs and size of our generated model are only 24. 46\% and 4. 86\% of the original model.
Optimization of Service Addition in Multilevel Index Model for Edge Computing
With the development of Edge Computing and Artificial Intelligence (AI) technologies, edge devices are witnessed to generate data at unprecedented volume.
ISTR: End-to-End Instance Segmentation with Transformers
However, such an upgrade is not applicable to instance segmentation, due to its significantly higher output dimensions compared to object detection.
Ranked #21 on
Instance Segmentation
on COCO test-dev
Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity
When primed with only a handful of training samples, very large, pretrained language models such as GPT-3 have shown competitive results when compared to fully-supervised, fine-tuned, large, pretrained language models.
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling robot learning by reusing past robotic data.
Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning
ZEUS trains a reinforcement learning agent that learns to adaptively modify the input video segments that are subsequently sent to an action classification network.
Learning to Estimate Hidden Motions with Global Motion Aggregation
We demonstrate that the optical flow estimates in the occluded regions can be significantly improved without damaging the performance in non-occluded regions.
Ranked #5 on
Optical Flow Estimation
on Sintel-final
Learning Optical Flow from a Few Matches
In this paper, we show that the dense correlation volume representation is redundant and accurate flow estimation can be achieved with only a fraction of elements in it.
Ranked #11 on
Optical Flow Estimation
on KITTI 2015 (train)
Visionary: Vision architecture discovery for robot learning
We propose a vision-based architecture search algorithm for robot manipulation learning, which discovers interactions between low dimension action inputs and high dimensional visual inputs.
Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles
Multi-document summarization is a challenging task for which there exists little large-scale datasets.
Disentangle Perceptual Learning through Online Contrastive Learning
Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on the pre-trained classification network to provide features, which are not necessarily optimal in terms of visual perception of image transformation.
Bidirectionally Self-Normalizing Neural Networks
The problem of vanishing and exploding gradients has been a long-standing obstacle that hinders the effective training of neural networks.
Taskology: Utilizing Task Relations at Scale
Many computer vision tasks address the problem of scene understanding and are naturally interrelated e. g. object classification, detection, scene segmentation, depth estimation, etc.
MedSRGAN: medical images super-resolution using generative adversarial networks
Super-resolution (SR) in medical imaging is an emerging application in medical imaging due to the needs of high quality images acquired with limited radiation dose, such as low dose Computer Tomography (CT), low field magnetic resonance imaging (MRI).
Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction
Automatic sentence summarization produces a shorter version of a sentence, while preserving its most important information.
Natural Language Generation for Effective Knowledge Distillation
Knowledge distillation can effectively transfer knowledge from BERT, a deep language representation model, to traditional, shallow word embedding-based neural networks, helping them approach or exceed the quality of other heavyweight language representation models.
Decoding of visual-related information from the human EEG using an end-to-end deep learning approach
Here, we proposed a CNNLSTM based neural network architecture termed EEG_CNNLSTMNet for the classification of EEG signals in response to grating stimuli with different spatial frequencies.
Prediction Modeling and Analysis for Telecom Customer Churn in Two Months
In this paper, we propose a new T+2 churn customer prediction model, in which the churn customers in two months are recognized and the one-month window T+1 is reserved to carry out churn management strategies.
Distributed Training Across the World
Traditional synchronous distributed training is performed inside a cluster, since it requires high bandwidth and low latency network (e. g. 25Gb Ethernet or Infini-band).
Cross-domain Aspect Category Transfer and Detection via Traceable Heterogeneous Graph Representation Learning
Aspect category detection is an essential task for sentiment analysis and opinion mining.
Mobile Video Action Recognition
In addition to motion vectors, we also provide a temporal fusion method to explicitly induce the temporal context.
Predictive Ensemble Learning with Application to Scene Text Detection
Taking scene text detection as the application, where no suitable ensemble learning strategy exists, PEL can significantly improve the performance, compared to either individual state-of-the-art models, or the fusion of multiple models by non-maximum suppression.
Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
In the natural language processing literature, neural networks are becoming increasingly deeper and complex.
Ranked #60 on
Sentiment Analysis
on SST-2 Binary classification
Cross-language Citation Recommendation via Hierarchical Representation Learning on Heterogeneous Graph
While the volume of scholarly publications has increased at a frenetic pace, accessing and consuming the useful candidate papers, in very large digital libraries, is becoming an essential and challenging task for scholars.
Crowd Counting with Density Adaption Networks
Crowd counting is one of the core tasks in various surveillance applications.
Block Mean Approximation for Efficient Second Order Optimization
Advanced optimization algorithms such as Newton method and AdaGrad benefit from second order derivative or second order statistics to achieve better descent directions and faster convergence rates.
An interpretable LSTM neural network for autoregressive exogenous model
In this paper, we propose an interpretable LSTM recurrent neural network, i. e., multi-variable LSTM for time series with exogenous variables.
Precise Temporal Action Localization by Evolving Temporal Proposals
The performances of existing action localization approaches remain unsatisfactory in precisely determining the beginning and the end of an action.
Devon: Deformable Volume Network for Learning Optical Flow
State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions.
Generative Adversarial Network for Abstractive Text Summarization
In this paper, we propose an adversarial process for abstractive text summarization, in which we simultaneously train a generative model G and a discriminative model D. In particular, we build the generator G as an agent of reinforcement learning, which takes the raw text as input and predicts the abstractive summarization.
Ranked #5 on
Text Summarization
on CNN / Daily Mail (Anonymized)
Abstractive Text Summarization
Generative Adversarial Network
+2
Learning Image Relations with Contrast Association Networks
A key to the problem is learning a representation of relations.
Evolving Boxes for Fast Vehicle Detection
We perform fast vehicle detection from traffic surveillance cameras.
Doubly Stochastic Neighbor Embedding on Spheres
To solve this problem, we introduce a fast normalization method and normalize the similarity matrix to be doubly stochastic such that all the data points have equal total similarities.
Coherent Parametric Contours for Interactive Video Object Segmentation
Interactive video segmentation systems aim at producing sub-pixel-level object boundaries for visual effect applications.
Detecting "Smart" Spammers On Social Network: A Topic Model Approach
Spammer detection on social network is a challenging problem.
Contour Flow: Middle-Level Motion Estimation by Combining Motion Segmentation and Contour Alignment
Our goal is to estimate contour flow (the contour pairs with consistent point correspondence) from inconsistent contours extracted independently in two video frames.
Unsupervised Learning on Neural Network Outputs: with Application in Zero-shot Learning
The outputs of a trained neural network contain much richer information than just an one-hot classifier.
Instance Significance Guided Multiple Instance Boosting for Robust Visual Tracking
Multiple Instance Learning (MIL) recently provides an appealing way to alleviate the drifting problem in visual tracking.
Abrupt Motion Tracking via Nearest Neighbor Field Driven Stochastic Sampling
Stochastic sampling based trackers have shown good performance for abrupt motion tracking so that they have gained popularity in recent years.
A Fast Projected Fixed-Point Algorithm for Large Graph Matching
In particular, with high accuracy, our algorithm takes only a few seconds (in a PC) to match two graphs of 1, 000 nodes.
Correlative Multi-Label Multi-Instance Image Annotation
The cross-level label coherence en-codes the consistency between the labels at the image leveland the labels at the region level.
