Ishita Dasgupta

Affiliations:
  • Google DeepMind
  • Princeton University, USA (former)


According to our database1, Ishita Dasgupta authored at least 36 papers between 2017 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
ReMI: A Dataset for Reasoning with Multiple Images.
CoRR, 2024

Scaling Instructable Agents Across Many Simulated Worlds.
CoRR, 2024

The Impact of Depth on Compositional Generalization in Transformer Language Models.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Plot Twist: Multimodal Models Don't Comprehend Simple Chart Details.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023
Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning.
PLoS Comput. Biol., 2023

The Impact of Depth and Width on Transformer Language Model Generalization.
CoRR, 2023

Hierarchical reinforcement learning with natural language subgoals.
CoRR, 2023

Meta-Learned Models of Cognition.
CoRR, 2023

Collaborating with language models for embodied reasoning.
CoRR, 2023

Passive learning of active causal strategies in agents and language models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Distilling Internet-Scale Vision-Language Models into Embodied Agents.
Proceedings of the International Conference on Machine Learning, 2023

2022
Transformers generalize differently from information stored in context vs in weights.
CoRR, 2022

Language models show human-like content effects on reasoning.
CoRR, 2022

Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning.
CoRR, 2022

Learning to Navigate Wikipedia by Taking Random Walks.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Learning Structure from the Ground up - Hierarchical Representation Learning by Chunking.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Using natural language and program abstractions to instill human inductive biases in machines.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Tell me why! Explanations support learning relational and causal structure.
Proceedings of the International Conference on Machine Learning, 2022

Distinguishing rule and exemplar-based generalization in learning systems.
Proceedings of the International Conference on Machine Learning, 2022

Can language models learn from explanations in context?
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

2021
Passive attention in artificial neural networks predicts human visual selectivity.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Meta-Learning of Structured Task Distributions in Humans and Machines.
Proceedings of the 9th International Conference on Learning Representations, 2021

Chunking as a Rational Solution to the Speed-Accuracy Trade-off in a Serial Reaction Time Task.
Proceedings of the 43rd Annual Meeting of the Cognitive Science Society, 2021

Are Convolutional Neural Networks or Transformers more like human vision?
Proceedings of the 43rd Annual Meeting of the Cognitive Science Society, 2021

How does mental sorting scale?
Proceedings of the 43rd Annual Meeting of the Cognitive Science Society, 2021

2020
Meta-Learning of Compositional Task Distributions in Humans and Machines.
CoRR, 2020

Analyzing Machine-Learned Representations: A Natural Language Case Study.
Cogn. Sci., 2020

2019
Causal Reasoning from Meta-reinforcement Learning.
CoRR, 2019

Heuristics, hacks, and habits: Boundedly optimal approaches to learning, reasoning and decision making.
Proceedings of the 41th Annual Meeting of the Cognitive Science Society, 2019

2018
Learning to act by integrating mental simulations and physical experiments.
Proceedings of the 40th Annual Meeting of the Cognitive Science Society, 2018

Evaluating Compositionality in Sentence Embeddings.
Proceedings of the 40th Annual Meeting of the Cognitive Science Society, 2018

2017
Amortized Hypothesis Generation.
Proceedings of the 39th Annual Meeting of the Cognitive Science Society, 2017

Markov Transitions between Attractor States in a Recurrent Neural Network.
Proceedings of the 2017 AAAI Spring Symposia, 2017


  Loading...