Generalization

[ICML23] MEWL: Few-shot multimodal word learning with referential uncertainty

Without explicit feedback, humans can rapidly learn the meaning of words. Children can acquire a new word after just a few passive …

Guangyuan Jiang, Manjie Xu, Shiji Xin, Wei Liang, Yujia Peng, Chi Zhang, Yixin Zhu

[ICML23] MEWL: Few-shot multimodal word learning with referential uncertainty

[ICML23] On the Complexity of Bayesian Generalization

We examine concept generalization at a large scale in the natural visual spectrum. Established computational modes (i.e., rule-based or …

Yu-Zhe Shi, Manjie Xu, John E. Hopcroft, Kun He, Joshua B. Tenenbaum, Song-Chun Zhu, Ying Nian Wu, Wenjuan Han, Yixin Zhu

[ICML23] On the Complexity of Bayesian Generalization

[ICLR23] A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics

Inspired by humans’ exceptional ability to master arithmetic and generalize to new problems, we present a new dataset, …

Qing Li, Siyuan Huang, Yining Hong, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu

[ICLR23] A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics

[ICRA23] GenDexGrasp: Generalizable Dexterous Grasping

Generating dexterous grasping has been a long-standing and challenging robotic task. Despite recent progress, existing methods …

Puhao Li, Tengyu Liu, Yuyang Li, Yiran Geng, Yixin Zhu, Yaodong Yang, Siyuan Huang

[arXiv22] To think inside the box, or to think out of the box? Scientific discovery via the reciprocation of insights and concepts

If scientific discovery is one of the main driving forces of human progress, insight is the fuel for the engine, which has long …

Yu-Zhe Shi, Manjie Xu, Wenjuan Han, Yixin Zhu

[arXiv22] Neural-Symbolic Recursive Machine for Systematic Generalization

Despite the tremendous success, existing machine learning models still fall short of human-like systematic generalization – …

Qing Li, Yixin Zhu, Yitao Liang, Ying Nian Wu, Song-Chun Zhu, Siyuan Huang

[arXiv21] HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving

Humans learn compositional and causal abstraction, i.e., knowledge, in response to the structure of naturalistic tasks. When presented …

Sirui Xie, Xiaojian Ma, Peiyu Yu, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu

[arXiv21] HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving