9 papers
Difficulty-Estimated Policy Optimization
Yu Zhao, Fan Jiang, Tianle Liu +4
Recent advancements in Large Reasoning Models (LRMs), exemplified by DeepSeek-R1, have underscored the potential of scaling inference-time compute through Group Relative Policy Opt…
CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher
Tianlun Liu, Zhiliang Tian, Zhen Huang +5
Text understanding often suffers from domain shifts. To handle testing domains, domain adaptation (DA) is trained to adapt to a fixed and observed testing domain; a more challengin…
Poisson-Process Topic Model for Integrating Knowledge from Pre-trained Language Models
Morgane Austern, Yuanchuan Guo, Zheng Tracy Ke +1
Topic modeling is traditionally applied to word counts without accounting for the context in which words appear. Recent advancements in large language models (LLMs) offer contextua…
LADY: Linear Attention for Autonomous Driving Efficiency without Transformers
Jihao Huang, Xi Xia, Zhiyuan Li +4
End-to-end autonomous driving has emerged as a promising paradigm. However, state-of-the-art methods rely heavily on Transformer architectures. The inherent quadratic complexity of…
A Looming of phantoms
Kimoi Kemboi, Daniel Krashen, Tianle Liu +6
Following Krah's method, we construct new examples of phantom categories as semiorthogonal components of the derived categories of two types of rational surfaces: the blowup of the…
A Heavily Right Strategy for Statistical Inference with Dependent Studies in Any Dimension
Tianle Liu, Xiao-Li Meng, Natesh S. Pillai
We leverage recent advances in heavy-tail approximations for global hypothesis testing with dependent studies to construct approximate confidence regions without modeling or estima…