5 citations · 10 across the 24 of their papers we have counts for
7 papers · 1 filter
Detecting Pretraining Data in Large Language Models from a Free-Energy Perspective
Chenye Ke, Zirui Liu, Qi Liu +4
Detecting pretraining data in large language models is challenging because high likelihood can reflect either training exposure or strong generalization. In the joint space of pred…
SocraticPO: Policy Optimization via Interactive Guidance
Zirui Liu, Tingyue Pan, Jie Ouyang +8
Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness. Such rewards provide an optimization dir…
StaTS: Spectral Trajectory Schedule Learning for Adaptive Time Series Forecasting with Frequency Guided Denoiser
Jintao Zhang, Zirui Liu, Mingyue Cheng +3
Diffusion models have been used for probabilistic time series forecasting and show strong potential. However, fixed noise schedules often produce intermediate states that are hard…
Towards Stable and Structured Time Series Generation with Perturbation-Aware Flow Matching
Jintao Zhang, Mingyue Cheng, Zirui Liu +3
Time series generation is critical for a wide range of applications, which greatly supports downstream analytical and decision-making tasks. However, the inherent temporal heteroge…
Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch
Ziyang Zhang, Xinheng Ding, Jiayi Yuan +4
Deterministic inference is increasingly critical for large language model (LLM) applications such as LLM-as-a-judge evaluation, multi-agent systems, and Reinforcement Learning (RL)…
Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
Wentao Guo, Jikai Long, Yimeng Zeng +9
Zeroth-order optimization (ZO) is a memory-efficient strategy for fine-tuning Large Language Models using only forward passes. However, the application of ZO fine-tuning in memory-…
Survey of Computerized Adaptive Testing: A Machine Learning Perspective
Yan Zhuang, Qi Liu, Haoyang Bi +12
Computerized Adaptive Testing (CAT) offers an efficient and personalized method for assessing examinee proficiency by dynamically adjusting test questions based on individual perfo…