activity
20242026
collaborators

8 papers

cs.CL2026

Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation

Xingyu Su, Jacob Helwig, Shubham Parashar +6

We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs). Rather than pretraining from scratch, prior work replaces the causal attention i…

cs.CL2026

Learnability-Informed Fine-Tuning of Diffusion Language Models

Shubham Parashar, Atharv Chagi, Jacob Helwig +5

We aim to improve the reasoning capabilities of diffusion language models (DLMs). While SFT is a popular post-training recipe for autoregressive models, its use in DLMs faces chall…

cs.LG2026

Orbital Transformers for Predicting Wavefunctions in Time-Dependent Density Functional Theory

Xuan Zhang, Haiyang Yu, Chengdong Wang +3

We aim to learn wavefunctions simulated by time-dependent density functional theory (TDDFT), which can be efficiently represented as linear combination coefficients of atomic orbit…

cs.LG2026

A Two-Phase Deep Learning Framework for Adaptive Time-Stepping in High-Speed Flow Modeling

Jacob Helwig, Sai Sreeharsha Adavi, Xuan Zhang +11

We consider the problem of modeling high-speed flows using machine learning methods. While most prior studies focus on low-speed fluid flows in which uniform time-stepping is pract…

cs.LG2026

Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency

Yuchao Lin, Jacob Helwig, Shurui Gui +1

We consider achieving equivariance in machine learning systems via frame averaging. Current frame averaging methods involve a costly sum over large frames or rely on sampling-based…

cs.LG2025

Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems

Xuan Zhang, Limei Wang, Jacob Helwig +60

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating…