1 citations · 3 across the 12 of their papers we have counts for
14 papers
ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL
Zelin He, Haotian Lin, Boran Han +6
Agentic reinforcement learning (RL) enables LLM agents to improve continuously from environment rewards, yet the resulting policies do not systematically accumulate reusable strate…
TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
Andrej Tschalzev, Nick Erickson, Yuyang Wang +4
Progress in tabular machine learning has largely focused on increasingly sophisticated model architectures. At the same time, feature engineering remains a critical yet underexplor…
Understanding the Implicit Biases of Design Choices for Time Series Foundation Models
Annan Yu, Danielle C. Maddix, Boran Han +7
Time series foundation models (TSFMs) are a class of potentially powerful, general-purpose tools for time series forecasting and related temporal tasks, but their behavior is stron…
Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility
Annan Yu, Danielle C. Maddix, Boran Han +7
Transformers are widely used across data modalities, and yet the principles distilled from text models often transfer imperfectly to models trained to other modalities. In this pap…
CrEst: Credibility Estimation for Contexts in LLMs via Weak Supervision
Dyah Adila, Shuai Zhang, Boran Han +2
The integration of contextual information has significantly enhanced the performance of large language models (LLMs) on knowledge-intensive tasks. However, existing methods often o…
End-to-End Probabilistic Framework for Learning with Hard Constraints
Utkarsh Utkarsh, Danielle C. Maddix, Ruijun Ma +2
We present ProbHardE2E, a probabilistic forecasting framework that incorporates hard operational/physical constraints, and provides uncertainty quantification. Our methodology uses…
MLZero: A Multi-Agent System for End-to-end Machine Learning Automation
Haoyang Fang, Boran Han, Nick Erickson +10
Existing AutoML systems have advanced the automation of machine learning (ML); however, they still require substantial manual configuration and expert input, particularly when hand…
Adapting to Online Distribution Shifts in Deep Learning: A Black-Box Approach
Dheeraj Baby, Boran Han, Shuai Zhang +3
We study the well-motivated problem of online distribution shift in which the data arrive in batches and the distribution of each batch can change arbitrarily over time. Since the…
Effectively Steer LLM To Follow Preference via Building Confident Directions
Bingqing Song, Boran Han, Shuai Zhang +5
Having an LLM that aligns with human preferences is essential for accommodating individual needs, such as maintaining writing style or generating specific topics of interest. The m…
Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization
Luca Masserano, Abdul Fatir Ansari, Boran Han +8
How to best develop foundational models for time series forecasting remains an important open question. Tokenization is a crucial consideration in this effort: what is an effective…
Comparing and Contrasting DLWP Backbones on Navier-Stokes and Atmospheric Dynamics
Matthias Karlbauer, Danielle C. Maddix, Abdul Fatir Ansari +5
A large number of Deep Learning Weather Prediction (DLWP) architectures -- based on various backbones, including U-Net, Transformer, Graph Neural Network, and Fourier Neural Operat…
Transferring Knowledge from Large Foundation Models to Small Downstream Models
Shikai Qiu, Boran Han, Danielle C. Maddix +3
How do we transfer the relevant knowledge from ever larger foundation models into small, task-specific downstream models that can run at much lower costs? Standard transfer learnin…
Discovering Bias in Latent Space: An Unsupervised Debiasing Approach
Dyah Adila, Shuai Zhang, Boran Han +1
The question-answering (QA) capabilities of foundation models are highly sensitive to prompt variations, rendering their performance susceptible to superficial, non-meaning-alterin…
Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs
S. Chandra Mouli, Danielle C. Maddix, Shima Alizadeh +4
Existing work in scientific machine learning (SciML) has shown that data-driven learning of solution operators can provide a fast approximate alternative to classical numerical par…