Victor Dibia
YOU?
Author Swipe
View article: Interactive Debugging and Steering of Multi-Agent AI Systems
Interactive Debugging and Steering of Multi-Agent AI Systems Open
Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users. What challenges do developers face when trying to build and debug these AI agent teams? In formative interviews with five AI …
View article: Challenges in Human-Agent Communication
Challenges in Human-Agent Communication Open
Remarkable advancements in modern generative foundation models have enabled the development of sophisticated and highly capable autonomous agents that can observe their environment, invoke tools, and communicate with other agents to solve …
View article: Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks Open
Modern AI agents, driven by advances in large foundation models, promise to enhance our productivity and transform our lives by augmenting our knowledge and capabilities. To achieve this vision, AI agents must effectively plan, perform mul…
View article: AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems
AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems Open
Multi-agent systems, where multiple agents (generative AI models + tools) collaborate, are emerging as an effective pattern for solving long-running, complex tasks in numerous domains. However, specifying their parameters (such as models, …
View article: Towards better Human-Agent Alignment: Assessing Task Utility in LLM-Powered Applications
Towards better Human-Agent Alignment: Assessing Task Utility in LLM-Powered Applications Open
The rapid development in the field of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents to assist humans in their daily tasks. However, a significant gap remains in assessin…
View article: Axiomatic Preference Modeling for Longform Question Answering
Axiomatic Preference Modeling for Longform Question Answering Open
The remarkable abilities of large language models (LLMs) like GPT-4 partially stem from post-training processes like Reinforcement Learning from Human Feedback (RLHF) involving human preferences encoded in a reward model. However, these re…
View article: LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models
LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models Open
Systems that support users in the automatic creation of visualizations must address several subtasks - understand the semantics of data, enumerate relevant visualization goals and generate visualization specifications. In this work, we pos…
View article: LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models
LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models Open
Systems that support users in the automatic creation of visualizations must address several subtasks - understand the semantics of data, enumerate relevant visualization goals and generate visualization specifications. In this work, we pos…
View article: Axiomatic Preference Modeling for Longform Question Answering
Axiomatic Preference Modeling for Longform Question Answering Open
The remarkable abilities of large language models (LLMs) like ChatGPT and GPT-4 partially stem from the post-training processes involving human preferences encoded within a reward model as part of a Reinforcement Learning from Human Feedba…
View article: Aligning Offline Metrics and Human Judgments of Value for Code Generation Models
Aligning Offline Metrics and Human Judgments of Value for Code Generation Models Open
Large language models have demonstrated great potential to assist programmers in generating code. For such human-AI pair programming scenarios, we empirically demonstrate that while generated code are most often evaluated in terms of their…
View article: Aligning Offline Metrics and Human Judgments of Value for Code Generation Models
Aligning Offline Metrics and Human Judgments of Value for Code Generation Models Open
Large language models have demonstrated great potential to assist programmers in generating code. For such human-AI pair programming scenarios, we empirically demonstrate that while generated code is most often evaluated in terms of their …
View article: NeuralQA: A Usable Library for Question Answering (Contextual Query\n Expansion + BERT) on Large Datasets
NeuralQA: A Usable Library for Question Answering (Contextual Query\n Expansion + BERT) on Large Datasets Open
Existing tools for Question Answering (QA) have challenges that limit their\nuse in practice. They can be complex to set up or integrate with existing\ninfrastructure, do not offer configurable interactive interfaces, and do not\ncover the…
View article: NeuralQA: A Usable Library for Question Answering (Contextual Query Expansion + BERT) on Large Datasets
NeuralQA: A Usable Library for Question Answering (Contextual Query Expansion + BERT) on Large Datasets Open
Existing tools for Question Answering (QA) have challenges that limit their use in practice. They can be complex to set up or integrate with existing infrastructure, do not offer configurable interactive interfaces, and do not cover the fu…
View article: Data2Vis: Automatic Generation of Data Visualizations Using Sequence-to-Sequence Recurrent Neural Networks
Data2Vis: Automatic Generation of Data Visualizations Using Sequence-to-Sequence Recurrent Neural Networks Open
Rapidly creating effective visualizations using expressive grammars is challenging for users who have limited time and limited skills in statistics and data visualization. Even high-level, dedicated visualization tools often require users …
View article: Beyond Heuristics: Learning Visualization Design
Beyond Heuristics: Learning Visualization Design Open
In this paper, we describe a research agenda for deriving design principles directly from data. We argue that it is time to go beyond manually curated and applied visualization design guidelines. We propose learning models of visualization…
View article: Designing for Democratization: Introducing Novices to Artificial Intelligence Via Maker Kits
Designing for Democratization: Introducing Novices to Artificial Intelligence Via Maker Kits Open
Existing research highlight the myriad of benefits realized when technology is sufficiently democratized and made accessible to non-technical or novice users. However, democratizing complex technologies such as artificial intelligence (AI)…
View article: A Cognitive Assistant for Visualizing and Analyzing Exoplanets
A Cognitive Assistant for Visualizing and Analyzing Exoplanets Open
We demonstrate an embodied cognitive agent that helps scientists visualize and analyze exo-planets and their host stars. The prototype is situated in a room equipped with a large display, microphones, cameras, speakers, and pointing device…