Joshua B. Tenenbaum

Professor@Massachusetts Institute of Technology·美国·OpenReview

研究方向

Computational cognitive science · Bayesian models of cognition · Cognitive AI · Common sense scene understanding · Computational models of cognitive development

Joshua B. Tenenbaum

Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People

ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning

Language and Experience: A Computational Model of Social Learning in Complex Tasks

Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents

PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement

Benchmarking World-Model Learning

Evaluating Language Models' Evaluations of Games

Code-enabled language models can outperform reasoning models on diverse tasks

Learning Linear Attention in Polynomial Time

VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning

Can Large Language Models Understand Symbolic Graphics Programs?

Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations

What Makes a Maze Look Like a Maze?

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains

Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models

Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models

Self-Steering Language Models