Honglak Lee

Robust Inference via Generative Classifiers for Handling Noisy Labels

2019 · arXiv (Cornell University)

Large-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern deep neural networks (DNNs) poorly generalize from such noisy training datasets. To mitigate the issue, we propose a …

Learning Deep Representations of Fine-grained Visual Descriptions

2016 · arXiv (Cornell University)

State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared …

A Simple Randomization Technique for Generalization in Deep Reinforcement Learning

2019 · arXiv (Cornell University)

Deep reinforcement learning (RL) agents often fail to generalize to unseen environments (yet semantically similar to trained agents), particularly when they are trained on high-dimensional state spaces, such as images. In this paper, we propose …

Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning

2020 · arXiv (Cornell University)

Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a challenging task. …

Evolving Reinforcement Learning Algorithms

2021 · arXiv (Cornell University)

We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. The learned algorithms are domain-agnostic …

TOD-Flow: Modeling the Structure of Task-Oriented Dialogues

2023 · arXiv (Cornell University)

Task-Oriented Dialogue (TOD) systems have become crucial components in interactive artificial intelligence applications. While recent advances have capitalized on pre-trained language models (PLMs), they exhibit limitations regarding transparency and controllability. To address these challenges, we …

Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning

2024

Instruction tuning has emerged as a powerful technique, significantly boosting zero-shot performance on unseen tasks.While recent work has explored cross-lingual generalization by applying instruction tuning to multilingual models, previous studies have primarily focused on English, …

Sentence Ordering and Coherence Modeling using Recurrent Neural Networks

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Modeling the structure of coherent texts is a key NLP problem. The task of coherently organizing a given set of sentences has been commonly used to build and evaluate models that understand such structure. We …

An efficient framework for learning sentence representations

2018 · arXiv (Cornell University)

In this work we propose a simple and efficient framework for learning sentence representations from unlabelled data. Drawing inspiration from the distributional hypothesis and recent work on learning sentence representations, we reformulate the problem of …

Content preserving text generation with attribute controls

2018 · arXiv (Cornell University)

In this work, we address the problem of modifying textual attributes of sentences. Given an input sentence and a set of attribute labels, we attempt to generate sentences that are compatible with the conditioning information. …