Kanishk Gandhi — accepted AI-conference papers

2024

Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels

Jan-Philipp Fränken, Eric Zelikman, Rafael Rafailov, Kanishk Gandhi, Tobias Gerstenberg, Noah Goodman

NeurIPS 2024poster

When prompting a language model (LM), users often expect the model to adhere to a set of behavioral principles across diverse tasks, such as producing insightful content while avoiding harmful or biased language. Instilling such principles (i.e., a constitution) into a model is resource-intensive, t…

Cited by 10 Source ↗PDF ↗code ↗Scholar ↗

2023

Understanding Social Reasoning in Language Models with Language Models

Kanishk Gandhi, Jan-Philipp Fränken, Tobias Gerstenberg, Noah Goodman

NeurIPS 2023spotlight

As Large Language Models (LLMs) become increasingly integrated into our everyday lives, understanding their ability to comprehend human mental states becomes critical for ensuring effective interactions. However, despite the recent attempts to assess the Theory-of-Mind (ToM) reasoning capabilities o…

Cited by 123 Source ↗PDF ↗Scholar ↗

2022

Eliciting Compatible Demonstrations for Multi-Human Imitation Learning

Kanishk Gandhi, Siddharth Karamcheti, Madeline Liao, Dorsa Sadigh

CoRL 2022poster

Imitation learning from human-provided demonstrations is a strong approach for learning policies for robot manipulation. While the ideal dataset for imitation learning is homogenous and low-variance - reflecting a single, optimal method for performing a task - natural human behavior has a great deal…

Cited by 22 Source ↗Scholar ↗

2021

Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others

Kanishk Gandhi, Gala Stojnic, Brenden M. Lake, Moira Rose Dillon

NeurIPS 2021poster

To achieve human-like common sense about everyday life, machine learning systems must understand and reason about the goals, preferences, and actions of other agents in the environment. By the end of their first year of life, human infants intuitively achieve such common sense, and these cognitive a…

Cited by 69 Source ↗PDF ↗Scholar ↗

2020

Mutual exclusivity as a challenge for deep neural networks

Kanishk Gandhi, Brenden M Lake

NeurIPS 2020poster

Strong inductive biases allow children to learn in fast and adaptable ways. Children use the mutual exclusivity (ME) bias to help disambiguate how words map to referents, assuming that if an object has one label then it does not need another. In this paper, we investigate whether or not vanilla neur…

Cited by 40 Source ↗PDF ↗Scholar ↗