10 citations · 16 across the 9 of their papers we have counts for
9 papers
TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
Yuanpeng Li, Gefei Lin, Annie Qu +1
Soft Actor-Critic (SAC) and its variants dominate Multi-Task Reinforcement Learning (MTRL) due to their off-policy sample efficiency, while on-policy methods such as Proximal Polic…
A Theoretical Analysis of Provable Compositional Generalization in Neural Networks: A Necessary and Sufficient Condition
Yuanpeng Li
Compositional generalization$\unicode{x2013}$the ability to systematically process novel combinations of known components$\unicode{x2013}$is a hallmark of human intelligence; howev…
Modern Hopfield Networks Require Chain-of-Thought to Solve -Hard Problems
Yang Cao, Xiaoyu Li, Yuanpeng Li +3
Modern Hopfield Networks (MHNs) have emerged as powerful components in deep learning, serving as effective replacements for pooling layers, LSTMs, and attention mechanisms. While r…
A Short Survey of Systematic Generalization
Yuanpeng Li
This survey includes systematic generalization and a history of how machine learning addresses it. We aim to summarize and organize the related information of both conventional and…
On a Built-in Conflict between Deep Learning and Systematic Generalization
Yuanpeng Li
In this paper, we hypothesize that internal function sharing is one of the reasons to weaken o.o.d. or systematic generalization in deep learning for classification tasks. Under eq…
Efficiently Disentangle Causal Representations
Yuanpeng Li, Joel Hestness, Mohamed Elhoseiny +2
This paper proposes an efficient approach to learning disentangled representations with causal mechanisms based on the difference of conditional probabilities in original and new d…
Concepts, Properties and an Approach for Compositional Generalization
Yuanpeng Li
Compositional generalization is the capacity to recognize and imagine a large amount of novel combinations from known components. It is a key in human intelligence, but current neu…
Compositional Generalization for Primitive Substitutions
Yuanpeng Li, Liang Zhao, Jianyu Wang +1
Compositional generalization is a basic mechanism in human language learning, but current neural networks lack such ability. In this paper, we conduct fundamental research for enco…
Zero-Shot Transfer VQA Dataset
Yuanpeng Li, Yi Yang, Jianyu Wang +1
Acquiring a large vocabulary is an important aspect of human intelligence. Onecommon approach for human to populating vocabulary is to learn words duringreading or listening, and t…