Search Results for author:
Found 10 papers, 3 papers with code
Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees
An LMUT is learned using a novel on-line algorithm that is well-suited for an active play setting, where the mimic learner observes an ongoing interaction between the neural net and the environment.
BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps
To this end, we propose BabyWalk, a new VLN agent that is learned to navigate by decomposing long instructions into shorter ones (BabySteps) and completing them sequentially.
Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks
Neural network models often generalize poorly to mismatched domains or distributions.
Iterative Vision-and-Language Navigation
We present Iterative Vision-and-Language Navigation (IVLN), a paradigm for evaluating language-guided agents navigating in a persistent environment over time.
Navigating Memory Construction by Global Pseudo-Task Simulation for Continual Learning
To provide an approximate solution to this problem in the online continual learning setting, we further propose the Global Pseudo-task Simulation (GPS), which mimics future catastrophic forgetting of the current task by permutation.
Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems
For vision-and-language reasoning tasks, both fully connectionist, end-to-end methods and hybrid, neuro-symbolic methods have achieved high in-distribution performance.
Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering
We train a language model (LM) to robustly answer multistep questions by generating and answering sub-questions.
Efficient End-to-End Visual Document Understanding with Rationale Distillation
Pre-processing tools, such as optical character recognition (OCR), can map document image inputs to textual tokens, then large language models (LLMs) can reason over text.
Does VLN Pretraining Work with Nonsensical or Irrelevant Instructions?
Data augmentation via back-translation is common when pretraining Vision-and-Language Navigation (VLN) models, even though the generated instructions are noisy.
Hybrid Transformer and Spatial-Temporal Self-Supervised Learning for Long-term Traffic Prediction
Long-term traffic prediction has always been a challenging task due to its dynamic temporal dependencies and complex spatial dependencies.
