Search Results for author:
Found 28 papers, 10 papers with code
Active World Model Learning in Agent-rich Environments with Progress Curiosity
World models are a family of predictive models that solve self-supervised problems on how the world evolves.
Building a Domain-specific Guardrail Model in Production
Generative AI holds the promise of enabling a range of sought-after capabilities and revolutionizing workflows in various consumer and enterprise verticals.
Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models
Multi-agent reinforcement learning (MARL) methods struggle with the non-stationarity of multi-agent systems and fail to adaptively learn online when tested with novel agents.
Learning Formal Mathematics From Intrinsic Motivation
We propose novel methods for hindsight relabeling on proof search trees to significantly improve the agent's sample efficiency in both tasks.
Tutorly: Turning Programming Videos Into Apprenticeship Learning Environments with LLMs
Online programming videos, including tutorials and streamcasts, are widely popular and contain a wealth of expert knowledge.
Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
Crucially, these improvements require no fine-tuning on these tasks.
Holodeck: Language Guided Generation of 3D Embodied AI Environments
3D simulated environments play a critical role in Embodied AI, but their creation requires expertise and extensive manual effort, restricting their diversity and scope.
Examining the Potential and Pitfalls of ChatGPT in Science and Engineering Problem-Solving
The study explores the capabilities of OpenAI's ChatGPT in solving different types of physics problems.
Generating and Evaluating Tests for K-12 Students with Language Model Simulations: A Case Study on Sentence Reading Efficiency
Developing an educational test can be expensive and time-consuming, as each item must be written by experts and then evaluated by collecting hundreds of student responses.
ContextRef: Evaluating Referenceless Metrics For Image Description Generation
None of the methods is successful with ContextRef, but we show that careful fine-tuning yields substantial improvements.
Hypothesis Search: Inductive Reasoning with Language Models
Inductive reasoning is a core problem-solving capacity: humans can identify underlying principles from a few examples, which robustly generalize to novel scenarios.
Curious Replay for Model-based Adaptation
Agents must be able to adapt quickly as an environment changes.
Just One Byte (per gradient): A Note on Low-Bandwidth Decentralized Language Model Finetuning Using Shared Randomness
Language model training in distributed settings is limited by the communication cost of gradient exchanges.
Developmental Curiosity and Social Interaction in Virtual Agents
We also find that learning a world model in the presence of an attentive caregiver helps the infant agent learn how to predict scenarios with challenging social and physical dynamics.
Measuring and Modeling Physical Intrinsic Motivation
Finally, linearly combining the adversarial model with the number of collisions in a scene leads to the greatest improvement in predictivity of human responses, suggesting humans are driven towards scenarios that result in high information gain and physical activity.
Partial-View Object View Synthesis via Filtered Inversion
At inference, given one or more views of a novel real-world object, FINV first finds a set of latent codes for the object by inverting the generative model from multiple initial seeds.
Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions
Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs.
Ranked #15 on
Code Generation
on HumanEval
Interaction Modeling with Multiplex Attention
Modeling multi-agent systems requires understanding how agents interact.
Challenges and Opportunities for Machine Learning Classification of Behavior and Mental State from Images
Computer Vision (CV) classifiers which distinguish and detect nonverbal social human behavior and mental state can aid digital diagnostics and therapeutics for psychiatry and the behavioral sciences.
Training Affective Computer Vision Models by Crowdsourcing Soft-Target Labels
While the F1-score for a one-hot encoded classifier is much higher (94. 33% vs. 78. 68%) with respect to the ground truth CAFE labels, the output probability vector of the crowd-trained classifier more closely resembles the distribution of human labels (t=3. 2827, p=0. 0014).
Improved Digital Therapy for Developmental Pediatrics Using Domain-Specific Artificial Intelligence: Machine Learning Study
Results: The classifier achieved a 66. 9% balanced accuracy and 67. 4% F1-score on the entirety of the Child Affective Facial Expression (CAFE) as well as a 79. 1% balanced accuracy and 78% F1-score on CAFE Subset A, a subset containing at least 60% human agreement on emotions labels.
Active World Model Learning with Progress Curiosity
Humans learn world models by curiously exploring their environment, in the process acquiring compact abstractions of high bandwidth sensory inputs, the ability to plan across long temporal horizons, and an understanding of the behavioral patterns of other agents.
ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation
We introduce ThreeDWorld (TDW), a platform for interactive multi-modal physical simulation.
A Wearable Social Interaction Aid for Children with Autism
With most recent estimates giving an incidence rate of 1 in 68 children in the United States, the autism spectrum disorder (ASD) is a growing public health crisis.
Learning to Play With Intrinsically-Motivated, Self-Aware Agents
We demonstrate that this policy causes the agent to explore novel and informative interactions with its environment, leading to the generation of a spectrum of complex behaviors, including ego-motion prediction, object attention, and object gathering.
Flexible Neural Representation for Physics Prediction
Humans have a remarkable capacity to understand the physical dynamics of objects in their environment, flexibly capturing complex structures and interactions at multiple levels of detail.
Emergence of Structured Behaviors from Curiosity-Based Intrinsic Motivation
Moreover, the world model that the agent learns supports improved performance on object dynamics prediction and localization tasks.
Learning to Play with Intrinsically-Motivated Self-Aware Agents
We demonstrate that this policy causes the agent to explore novel and informative interactions with its environment, leading to the generation of a spectrum of complex behaviors, including ego-motion prediction, object attention, and object gathering.
