Search Results for author:
Found 15 papers, 5 papers with code
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
FoveaTer: Foveated Transformer for Image Classification
Our proposed model pools the image features using squared pooling regions, an approximation to the biologically-inspired foveated architecture, and uses the pooled features as an input to a Transformer Network.
Open Question Answering over Tables and Text
In open question answering (QA), the answer to a question is produced by retrieving and then analyzing documents that might contain answers to the question.
Ranked #1 on
Question Answering
on OTT-QA
The gem5 Simulator: Version 20.0+
The open-source and community-supported gem5 simulator is one of the most popular tools for computer architecture research.
Hardware Architecture
GAT-GMM: Generative Adversarial Training for Gaussian Mixture Models
Motivated by optimal transport theory, we design the zero-sum game in GAT-GMM using a random linear generator and a softmax-based quadratic discriminator architecture, which leads to a non-convex concave minimax optimization problem.
HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data
3) a hybrid model that combines heterogeneous information to find the answer.
Ranked #4 on
Question Answering
on HybridQA
Meta Module Network for Compositional Visual Reasoning
To design a more powerful NMN architecture for practical use, we propose Meta Module Network (MMN) centered on a novel meta module, which can take in function recipes and morph into diverse instance modules dynamically.
Fine-tune Bert for DocRED with Two-step Process
Modelling relations between multiple entities has attracted increasing attention recently, and a new dataset called DocRED has been collected in order to accelerate the research on the document-level relation extraction.
Ranked #47 on
Relation Extraction
on DocRED
Generalized Natural Language Grounded Navigation via Environment-agnostic Multitask Learning
Recent research efforts enable study for natural language grounded navigation in photo-realistic environments, e. g., following natural language instructions or dialog.
How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection
Under deep neural networks, a pre-defined vocabulary is required to vectorize text inputs.
Scene Graph Generation via Conditional Random Fields
Scene graph, a graph representation of images that captures object instances and their relationships, offers a comprehensive understanding of an image.
A Variational Dirichlet Framework for Out-of-Distribution Detection
With the recently rapid development in deep learning, deep neural networks have been widely adopted in many real-life applications.
MOHONE: Modeling Higher Order Network Effects in KnowledgeGraphs via Network Infused Embeddings
First, we introduce methods that learn network representations of entities in the knowledge graph capturing these varied aspects of similarity.
Variational Knowledge Graph Reasoning
Inferring missing links in knowledge graphs (KG) has attracted a lot of attention from the research community.
Safer Classification by Synthesis
We posit that a generative approach is the natural remedy for this problem, and propose a method for classification using generative models.
