11 citations · 36 across the 11 of their papers we have counts for
11 papers
Human-Guided Complexity-Controlled Abstractions
Andi Peng, Mycal Tucker, Eoin Kenny +3
Neural networks often learn task-specific latent representations that fail to generalize to novel settings or tasks. Conversely, humans learn discrete representations (i.e., concep…
An Information Bottleneck Characterization of the Understanding-Workload Tradeoff
Lindsay Sanneman, Mycal Tucker, Julie Shah
Recent advances in artificial intelligence (AI) have underscored the need for explainable AI (XAI) to support human understanding of AI systems. Consideration of human factors that…
Towards True Lossless Sparse Communication in Multi-Agent Systems
Seth Karten, Mycal Tucker, Siva Kailas +1
Communication enables agents to cooperate to achieve their goals. Learning when to communicate, i.e., sparse (in time) communication, and whom to message is particularly important…
Towards Human-Agent Communication via the Information Bottleneck Principle
Mycal Tucker, Julie Shah, Roger Levy +1
Emergent communication research often focuses on optimizing task-specific utility as a driver for communication. However, human languages appear to evolve under pressure to efficie…
Prototype Based Classification from Hierarchy to Fairness
Mycal Tucker, Julie Shah
Artificial neural nets can represent and classify many types of data but are often tailored to particular applications -- e.g., for "fair" or "hierarchical" classification. Once an…
When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes
Mycal Tucker, Tiwalayo Eisape, Peng Qian +2
Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield "false negative" causality results: models…
Probe-Based Interventions for Modifying Agent Behavior
Mycal Tucker, William Kuhl, Khizer Shahid +3
Neural nets are powerful function approximators, but the behavior of a given neural net, once trained, cannot be easily modified. We wish, however, for people to be able to influen…
Interpretable Learned Emergent Communication for Human-Agent Teams
Seth Karten, Mycal Tucker, Huao Li +3
Learning interpretable communication is essential for multi-agent and human-agent teams (HATs). In multi-agent reinforcement learning for partially-observable environments, agents…
Emergent Discrete Communication in Semantic Spaces
Mycal Tucker, Huao Li, Siddharth Agrawal +4
Neural agents trained in reinforcement learning settings can learn to communicate among themselves via discrete tokens, accomplishing as a team what agents would be unable to do al…
What if This Modified That? Syntactic Interventions via Counterfactual Embeddings
Mycal Tucker, Peng Qian, Roger Levy
Neural language models exhibit impressive performance on a variety of tasks, but their internal reasoning may be difficult to understand. Prior art aims to uncover meaningful prope…
Adversarially Guided Self-Play for Adopting Social Conventions
Mycal Tucker, Yilun Zhou, Julie Shah
Robotic agents must adopt existing social conventions in order to be effective teammates. These social conventions, such as driving on the right or left side of the road, are arbit…