Search Results for author:
Found 11 papers, 4 papers with code
Human-Centered Planning
The vision of creating AI-powered personal assistants also involves creating structured outputs, such as a plan for one's day, or for an overseas trip.
Pretrained Language Models as Visual Planners for Human Assistance
Given a succinct natural language goal, e. g., "make a shelf", and a video of the user's progress so far, the aim of VPA is to devise a plan, i. e., a sequence of actions such as "sand shelf", "paint shelf", etc.
EgoTV: Egocentric Task Verification from Natural Language Task Descriptions
The goal in EgoTV is to verify the execution of tasks from egocentric videos based on the natural language description of these tasks.
Effective Baselines for Multiple Object Rearrangement Planning in Partially Observable Mapped Environments
This requires efficient trade-offs between exploration of the environment and planning for rearrangement, which is challenging because of long-horizon nature of the problem.
Action Dynamics Task Graphs for Learning Plannable Representations of Procedural Tasks
Given video demonstrations and paired narrations of an at-home procedural task such as changing a tire, we present an approach to extract the underlying task structure -- relevant actions and their temporal dependencies -- via action-centric task graphs.
Differentiable Approximations for Multi-resource Spatial Coverage Problems
Resource allocation for coverage of physical spaces is a challenging problem in robotic surveillance, mobile sensor networks and security domains.
An Examination of Preference-based Reinforcement Learning for Treatment Recommendation
Treatment recommendation is a complex multi-faceted problem with many conflicting objectives, e. g., optimizing the survival rate (or expected lifetime), mitigating negative impacts, reducing financial expenses and time costs, avoiding over-treatment, etc.
Multi-agent Trajectory Prediction with Fuzzy Query Attention
Trajectory prediction for scenes with multiple agents and entities is a challenging problem in numerous domains such as traffic prediction, pedestrian tracking and path planning.
PolSIRD: Modeling Epidemic Spread under Intervention Policies
Epidemic spread in a population is traditionally modeled via compartmentalized models which represent the free evolution of disease in absence of any intervention policies.
DynGEM: Deep Embedding Method for Dynamic Graphs
The major advantages of DynGEM include: (1) the embedding is stable over time, (2) it can handle growing dynamic graphs, and (3) it has better running time than using static embedding methods on each snapshot of a dynamic graph.
Social and Information Networks
Deep Generative Dual Memory Network for Continual Learning
This phenomenon called catastrophic forgetting is a fundamental challenge to overcome before neural networks can learn continually from incoming data.
