Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations
Large language models (LLMs) have emerged as powerful and general solutions to many natural language tasks. However, many of the most important applic...
see more
Find all the Top AICustomer Service papers. Links to pdf, code repos and demos are provided.
Large language models (LLMs) have emerged as powerful and general solutions to many natural language tasks. However, many of the most important applic...
see more
Introduces the Deep Off-Policy Evaluation (DOPE) benchmark, aimed at standardizing the evaluation of off-policy evaluation (OPE) methods in reinforcem...
see more
We describe a method for selecting relevant new training data for the LSTM-based domain selection component of our personal assistant system. Adding m...
see more
SurveyX is a system for automated survey generation using Large Language Models (LLMs), addressing challenges related to context window limitations an...
see more
The recent boom of AI has seen the emergence of many human-computer
conversation systems such as Google Assistant, Microsoft Cortana, Amazon Echo
and ...
see more
Controlling robots to perform tasks via natural language is one of the most challenging topics in human-robot interaction. In this work, we present a ...
see more
Explores the prediction of user intent in multi-turn information-seeking conversations, focusing on challenges faced by conversational assistants. The...
see more
Building multi-turn information-seeking conversation systems is an important
and challenging research topic. Although several advanced neural text mat...
see more
Presents the Gemini 1.5 family of multimodal models, which showcases advancements in recalling and reasoning over extensive contexts of up to 10 milli...
see more
Presents a neural conversational model that leverages the sequence-to-sequence learning framework to generate dialogue. It highlights the model's abil...
see more
Recognizing and comprehending human actions and gestures is a crucial perception requirement for robots to interact with humans and carry out tasks in...
see more
Presents the Neuro-Symbolic Concept Learner (NS-CL), a model designed to learn visual concepts, words, and semantic parsing of sentences using natural...
see more