Search Results for author:
Found 38 papers, 17 papers with code
Speculative Decoding with Big Little Decoder
To address this, we propose Big Little Decoder (BiLD), a framework that can improve inference efficiency and latency for a wide range of text generation applications.
$IC^3$: Image Captioning by Committee Consensus
If you ask a human to describe an image, they might do so in a thousand different ways.
Distribution Aware Metrics for Conditional Natural Language Generation
In this work we argue that existing metrics are not appropriate for domains such as visual description or summarization where ground truths are semantically diverse, and where the diversity in those captions captures useful additional information about the context.
LAVA: Language Audio Vision Alignment for Contrastive Video Pre-Training
Generating representations of video data is of key importance in advancing the field of machine perception.
An Embedding-Dynamic Approach to Self-supervised Learning
It also uses a purely-dynamic local dispersive force (Brownian motion) that shows improved performance over other methods and does not require knowledge of other particle coordinates.
Towards Understanding How Machines Can Learn Causal Overhypotheses
Recent work in machine learning and cognitive science has suggested that understanding causal information is essential to the development of intelligence.
Learning Causal Overhypotheses through Exploration in Children and Computational Models
Despite recent progress in reinforcement learning (RL), RL algorithms for exploration still remain an active area of research.
Misinformation Detection in Social Media Video Posts
With the growing adoption of short-form video by social media platforms, reducing the spread of misinformation through video posts has become a critical challenge for social media providers.
NewsPod: Automatic and Interactive News Podcasts
News podcasts are a popular medium to stay informed and dive deep into news topics.
Sketch-based Creativity Support Tools using Deep Learning
Sketching is a natural and effective visual communication medium commonly used in creative processes.
Compressive Visual Representations
We verify this by developing SimCLR and BYOL formulations compatible with the Conditional Entropy Bottleneck (CEB) objective, allowing us to both measure and control the amount of compression in the learned representation, and observe their impact on downstream tasks.
Ranked #31 on
Self-Supervised Image Classification
on ImageNet
DCUR: Data Curriculum for Teaching via Samples with Reinforcement Learning
Then, students learn by running either offline RL or by using teacher data in combination with a small amount of self-generated data.
What's The Latest? A Question-driven News Chatbot
This work describes an automatic news chatbot that draws content from a diverse set of news articles and creates conversations with a user about the news.
The Summary Loop: Learning to Write Abstractive Summaries Without Examples
This work presents a new approach to unsupervised abstractive summarization based on maximizing a combination of coverage and fluency for a given length constraint.
Ranked #48 on
Abstractive Text Summarization
on CNN / Daily Mail
Active Learning for Video Description With Cluster-Regularized Ensemble Ranking
Automatic video captioning aims to train models to generate text descriptions for all segments in a video, however, the most effective approaches require large amounts of manual annotation which is slow and expensive.
Predictive Information Accelerates Learning in RL
The Predictive Information is the mutual information between the past and the future, I(X_past; X_future).
A Dataset and Benchmarks for Multimedia Social Analysis
We present a new publicly available dataset with the goal of advancing multi-modality learning by offering vision and language data within the same context.
Scones: Towards Conversational Authoring of Sketches
Iteratively refining and critiquing sketches are crucial steps to developing effective designs.
Exploring Exploration: Comparing Children with RL Agents in Unified Environments
Research in developmental psychology consistently shows that children explore the world thoroughly and efficiently and that this exploration allows them to learn.
Measuring the Reliability of Reinforcement Learning Algorithms
To aid RL researchers and production users with the evaluation and improvement of reliability, we propose a set of metrics that quantitatively measure different aspects of reliability.
Grounding Human-to-Vehicle Advice for Self-driving Vehicles
We show that taking advice improves the performance of the end-to-end network, while the network cues on a variety of visual features that are provided by advice.
ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations
Learning from demonstrations is a popular tool for accelerating and reducing the exploration requirements of reinforcement learning.
Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor
In 180 physical experiments with the da Vinci Research Kit (dVRK) surgical robot, RGBD policies trained in simulation attain coverage of 83% to 95% depending on difficulty tier, suggesting that effective fabric smoothing policies can be learned from an algorithmic supervisor and that depth sensing is a valuable addition to color alone.
Evaluating Protein Transfer Learning with TAPE
Semi-supervised learning has emerged as an important paradigm in protein modeling due to the high cost of acquiring supervised protein labels, but the current literature is fragmented when it comes to datasets and standardized evaluation techniques.
Risk Averse Robust Adversarial Reinforcement Learning
In this paper we introduce risk-averse robust adversarial reinforcement learning (RARARL), using a risk-averse protagonist and a risk-seeking adversary.
Periphery-Fovea Multi-Resolution Driving Model guided by Human Attention
Inspired by human vision, we propose a new periphery-fovea multi-resolution driving model that predicts vehicle speed from dash camera videos.
Deep Transfer Learning of Pick Points on Fabric for Robot Bed-Making
We compare coverage results from (1) human supervision, (2) a baseline of picking at the uppermost blanket point, and (3) learned pick points.
Label and Sample: Efficient Training of Vehicle Object Detector from Sparsely Labeled Data
First, we note that an optimal subset (relative to all the objects encountered and labeled) of labeled objects in images can be obtained by importance sampling using gradients of the recognition network.
Textual Explanations for Self-Driving Vehicles
Finally, we explore a version of our model that generates rationalizations, and compare with introspective explanations on the same video segments.
Fast and Reliable Autonomous Surgical Debridement with Cable-Driven Robots Using a Two-Phase Calibration Procedure
In Phase II (fine), the bias from Phase I is applied to move the end-effector toward a small set of specific target points on a printed sheet.
Robotics
Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention
The attention model highlights image regions that potentially influence the network's output.
General models for rational cameras and the case of two-slit projections
The rational camera model recently introduced in [19] provides a general methodology for studying abstract nonlinear imaging systems and their multi-view geometry.
An Efficient Minibatch Acceptance Test for Metropolis-Hastings
We present a novel Metropolis-Hastings method for large datasets that uses small expected-size minibatches of data.
Fast Parallel SAME Gibbs Sampling on General Discrete Bayesian Networks
A fundamental task in machine learning and related fields is to perform inference on Bayesian networks.
SAME but Different: Fast and High-Quality Gibbs Parameter Estimation
SAME (State Augmentation for Marginal Estimation) \cite{Doucet99, Doucet02} is an approach to MAP parameter estimation which gives improved parameter estimates over direct Gibbs sampling.
Sparse Allreduce: Efficient Scalable Communication for Power-Law Data
Many large datasets exhibit power-law statistics: The web graph, social networks, text data, click through data etc.
Factor Modeling for Advertisement Targeting
We adapt a probabilistic latent variable model, namely GaP (Gamma-Poisson), to ad targeting in the contexts of sponsored search (SS) and behaviorally targeted (BT) display advertising.
