Theory
1,949 items in 14 lists
-
Toward Causal Representation Learning cardiacmr.hms.harvard.edu
Proceedings of the IEEE, 2021. [All Versions]. Yoshua Bengio's review on the perspective of treating causal inference as a representation learning problem.
-
Synthesizing theories of human language with Bayesian program induction cap.csail.mit.edu
Nature Communications, 2022. [All Versions].
-
Generalization, similarity, and Bayesian inference cambridge.org
Behavioral and Brain Sciences, 2001. [All Versions]. [Preprint]. Shepard has argued that a universal law should govern generalization across different domains of perception and cognition, as well as across organisms from different species or even different planets. Starting…
-
Building Machines That Learn and Think Like People cambridge.org
Behavioral and Brain Sciences, 2017. [All Versions]. [Preprint]. Recent progress in artificial intelligence has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as…
-
Why Imaginary Worlds? The psychological foundations and cultural evolution of fictions with imaginary worlds cambridge.org
Behavioral and Brain Sciences, 2021. [All Versions]. Imaginary worlds are extremely successful. The most popular fictions produced in the last few decades contain such a fictional world. They can be found in all fictional media, from novels (e.g., Lord of The Rings and Harry…
-
Rationalization is rational cambridge.org
Behavioral and Brain Sciences, 2020. [All Versions]. [Preprint]. Rationalization occurs when a person has performed an action and then concocts the beliefs and desires that would have made it rational. Then, people often adjust their own beliefs and desires to match the…
-
Insight solutions are correct more often than analytic solutions bpb-us-e1.wpmucdn.com
Thinking & Reasoning, 2016. [All Versions].
-
A high-level programming language for generative protein design biorxiv.org
2022. [All Versions]. Combining a basic set of building blocks into more complex forms is a universal design principle. Most protein designs have proceeded from a manual bottom-up approach using parts created by nature, but top-down design of proteins is fundamentally hard due…
-
Different computational relations in language are captured by distinct brain systems bilab.bnu.edu.cn
Cerebral Cortex, 2022. [All Versions].
-
Organizational Principles of Abstract Words in the Human Brain bilab.bnu.edu.cn
Cerebral Cortex, 2018. [All Versions].
-
Iconicity: From sign to system in human communication and language benjamins.com
Pragmatics & Cognition, 2014. [All Versions]. This paper explores the role of iconicity in spoken language and other human communication systems.
-
Levels of Analysis for Machine Learning baicsworkshop.github.io
ICLR'20 Bridging AI and Cognitive Science Workshop, 2020. [All Versions]. A Marr's paradigm account on machine learning.
-
Pixelor: A Competitive Sketching AI Agent. So you think you can beat me? ayankumarbhunia.github.io
ACM SIGGRAPH'20, 2020. [All Versions]. [Project]. Rationality in feature sketching.
-
Reducing the dimensionality of data with neural networks asset-pdf.scinapse.io
Science, 2006. [All Versions]. The original paper on Variational Autoencoder.
-
From Explicit Communication to Tacit Cooperation: A Novel Paradigm for Cooperative MARL arxiv.org
AAMAS'24, 2024. [All Versions]. Drawing inspiration from human team cooperative learning, this paper proposes a novel paradigm that facilitates a gradual shift from explicit communication to tacit cooperation.
-
Identifying concept libraries from language about object structure arxiv.org
CogSci'22, 2022. [All Versions].
-
Automated Reinforcement Learning (AutoRL): A Survey and Open Problems arxiv.org
2022. [All Versions]. A comprehensive review on AutoRL.
-
Discovering State and Action Abstractions for Generalized Task and Motion Planning arxiv.org
AAAI'22, 2022. [All Versions].
-
Meta-Interpretive Learning as Metarule Specialisation arxiv.org
Machine Learning, 2021. [All Versions].
-
Visual scoping operations for physical assembly arxiv.org
CogSci'21, 2021. [All Versions].
-
Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution arxiv.org
CVPR'21, 2021. [All Versions].
-
Fast and flexible: Human program induction in abstract reasoning tasks arxiv.org
CogSci'21, 2021. [All Versions].
-
Neural Production Systems arxiv.org
ICML'21, 2021. [All Versions]. Yoshua Bengio's perspective on slot attention model as a general production system.
-
Intentonomy: a Dataset and Study towards Human Intent Understanding arxiv.org
CVPR'21, 2021. [All Versions]. A large-scale database on human intentionally-posted images on social media.
-
An overview of multi-agent reinforcement learning from game theoretical perspective arxiv.org
2020. [All Versions]. Yaodong Yang's review on multi-agent reinforcement learning from the perspective of game theory.
-
Abductive Knowledge Induction From Raw Data arxiv.org
IJCAI'21, 2021. [All Versions].
-
Grounded Language Learning Fast and Slow arxiv.org
ICLR'21, 2021. [All Versions]. [Project].
-
Compositional Generalization via Neural-Symbolic Stack Machines arxiv.org
NeurIPS'20, 2020. [All Versions].
-
Neuro-Symbolic Visual Reasoning: Disentangling “Visual” from “Reasoning” arxiv.org
ICML'20, 2020. [All Versions].
-
Noise or Signal: The Role of Backgrounds in Image Classification arxiv.org
ICLR'21, 2021. [All Versions]. [Code & Data]. [Project]. A perspective on image background provides strong clue for foreground classification.
-
Analogy as Nonparametric Bayesian Inference over Relational Systems arxiv.org
CogSci'20, 2020. [All Versions].
-
Learning programs by learning from failures arxiv.org
Machine Learning, 2020. [All Versions].
-
PIQA: Reasoning about Physical Commonsense in Natural Language arxiv.org
AAAI'20, 2020. [All Versions].
-
An Explicitly Relational Neural Network Architecture arxiv.org
ICML'20, 2020. [All Versions].
-
ICLR'19, 2019. [All Versions].
-
Neural Logic Machines arxiv.org
ICLR'19, 2019. [All Versions].
-
Neural Logic Reinforcement Learning arxiv.org
ICML'19, 2019. [All Versions].
-
Few-shot Bayesian imitation learning with logical program policies. arxiv.org
AAAI'20, 2020. [All Versions].
-
Multi-Agent Cooperation and the Emergence of (Natural) Language arxiv.org
ICLR'17, 2017. [All Versions]. The original paper on the emergence of language in multi-agent reinforcement learning.
-
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge arxiv.org
AAAI'17, 2017. [All Versions]. Latest version of ConceptNet.
-
Representation Learning: A Review and New Perspectives arxiv.org
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013. [All Versions]. Yoshua Bengio's review on representation learning.
-
MoVer: Motion Verification for Motion Graphics Animations arxiv.org
ACM Transactions on Graphics, 2025. [All Versions]. While large vision-language models can generate motion graphics animations from text prompts, they regularly fail to include all of spatio-temporal properties described in the prompt. This work introduces MoVer, a motion…
-
The Scene Language: Representing Scenes with Programs, Words, and Embeddings arxiv.org
CVPR'25, 2025. [All Versions]. [Project]. This paper introduces the Scene Language, a visual scene representation that concisely and precisely describes the structure, semantics, and identity of visual scenes. It represents a scene with three key components: a program that…
-
War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars arxiv.org
2023. [All Versions].
-
The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4 arxiv.org
Microsoft Research AI4Science, 2023. [All Versions]. [Project]. A survey on the performance of LLMs within the context of scientific discovery, focusing on GPT-4.
-
ChipNeMo: Domain-Adapted LLMs for Chip Design arxiv.org
2023. [All Versions]. ChipNeMo aims to explore the applications of large language models (LLMs) for industrial chip design. Instead of directly deploying off-the-shelf commercial or open-source LLMs, the authors instead adopt the following domain adaptation techniques…
-
Human Comprehensible Active Learning of Genome-Scale Metabolic Networks arxiv.org
AAAI Spring Symposium Series 2023 on Computational Scientific Discovery, 2023. [All Versions]. [Extended Abstract]. [Slides]. This work introduces a novel machine learning framework ILP-iML1515 based on Inductive Logic Programming (ILP) that performs abductive logical reasoning…
-
Large Language Models for Software Engineering: A Systematic Literature Review arxiv.org
2023. [All Versions]. A systematic literature review on LLM4SE, with a particular focus on understanding how LLMs can be exploited to optimize processes and outcomes.
-
The SocialAI School: Insights from Developmental Psychology Towards Artificial Socio-Cultural Agents arxiv.org
ICML'23 Workshop on Theory-of-Mind, 2023. [All Versions]. [Project].
-
2023. [All Versions]. Rational meaning construction, a computational framework for language-informed thinking that combines neural language models with probabilistic models for rational inference. Linguistic meaning is framed as a context-sensitive mapping from natural language…
- next page of items loading…
