4 papers
Ask to Learn: Query-Based Collaborative Reinforcement Learning
Kaicheng Zhang, Hongqian Niu, Laixi Shi +3
Offline reinforcement learning is fundamentally limited by the coverage of the available data, while collecting additional trajectories through online exploration may be costly, un…
Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training
Kevin Wang, Hongqian Niu, Didong Li
As artificial intelligence (AI)-generated content proliferates, models are increasingly trained on their own outputs, risking progressive degradation or collapse. In this article,…
Incorporating LLM Embeddings for Variation Across the Human Genome
Hongqian Niu, Jordan Bryan, Jacob Williams +5
Recent advances in large language model (LLM) embeddings have enabled powerful representations for biological data, but most applications to date focus on gene-level information. W…
Deep Generative Models: Complexity, Dimensionality, and Approximation
Kevin Wang, Hongqian Niu, Yixin Wang +1
Generative networks have shown remarkable success in learning complex data distributions, particularly in generating high-dimensional data from lower-dimensional inputs. While this…