activity
20242026
collaborators

9 papers

cs.LG2026

Cold-Start Forecasting of New Product Life-Cycles via Conditional Diffusion Models

Ruihan Zhou, Zishi Zhang, Jinhui Han +2

Forecasting the life-cycle trajectory of a newly launched product is important for launch planning, resource allocation, and early risk assessment. This task is especially difficul…

cs.CL2026

SACRED: A Faithful Annotated Multimedia Multimodal Multilingual Dataset for Classifying Connectedness Types in Online Spirituality

Qinghao Guan, Yuchen Pan, Donghao Li +6

In religion and theology studies, spirituality has garnered significant research attention for the reason that it not only transcends culture but offers unique experience to each i…

cs.LG2026

Optimal low-rank stochastic gradient estimation for LLM training

Zehao Li, Tao Ren, Zishi Zhang +2

Large language model (LLM) training is often bottlenecked by memory constraints and stochastic gradient noise in extremely high-dimensional parameter spaces. Motivated by empirical…

cs.LG2026

Nonparametric Bayesian Optimization for General Rewards

Zishi Zhang, Tao Ren, Yijie Peng

This work focuses on Bayesian optimization (BO) under reward model uncertainty. We propose the first BO algorithm that achieves no-regret guarantee in a general reward setting, req…

cs.LG2026

LLM-Inspired Pretrain-Then-Finetune for Small-Data, Large-Scale Optimization

Zishi Zhang, Jinhui Han, Ming Hu +1

We consider small-data, large-scale decision problems in which a firm must make many operational decisions simultaneously (e.g., across a large product portfolio) while observing o…

cs.LG2025

RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training

Tao Ren, Jinyang Jiang, Hui Yang +10

Reinforcement learning with verifiable reward has recently emerged as a central paradigm for post-training large language models (LLMs); however, prevailing mean-based methods, suc…