6 papers
DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution
Nan Jia, Wenxuan Shi, Jingqing Ruan +11
General-purpose agents are increasingly expected to perform professional analytics work, which requires sustained reasoning, iterative investigation, and reliable evidence. Trainin…
WorldCast: Exploring Intelligent Visual Generation in World State Prediction
Wenhao Yan, Haodong Li, Xiaotong Li +9
Humans interpret multimodal observations of the world and forecast how it will evolve. Recent multimodal generative systems have demonstrated similar capabilities: they can integra…
Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
Nan Jia, Haojin Yang, Xing Ma +6
On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy distillation and standard reinforcement lea…
An Empirical Framework for Evaluating Semantic Preservation Using Hugging Face
Nan Jia, Anita Raja, Raffi Khatchadourian
As machine learning (ML) becomes an integral part of high-autonomy systems, it is critical to ensure the trustworthiness of learning-enabled software systems (LESS). Yet, the nonde…
Speculative Automated Refactoring of Imperative Deep Learning Programs to Graph Execution
Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh +2
Efficiency is essential to support ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code -- s…
M-DEW: Extending Dynamic Ensemble Weighting to Handle Missing Values
Adam Catto, Nan Jia, Ansaf Salleb-Aouissi +1
Missing value imputation is a crucial preprocessing step for many machine learning problems. However, it is often considered as a separate subtask from downstream applications such…