10 papers
Alternating Levenberg-Marquardt Training of Physics-Informed Neural Networks with Fourier-Enhanced Features
Yulun Wu, Matthieu Barreau, Miguel Aguiar +1
Physics-informed neural networks (PINNs) often fail to accurately resolve partial differential equations (PDEs) with high-frequency or multi-scale solutions, as well as strongly no…
Bridging the Divide: End-to-End Sequence-Graph Learning
Yuen Chen, Yulun Wu, Samuel Sharpe +5
Many real-world prediction tasks, particularly those involving entities such as customers or patients, involve both {sequential} and {relational} data. Each entity maintains its ow…
AOMGen: Photoreal, Physics-Consistent Demonstration Generation for Articulated Object Manipulation
Yulu Wu, Jiujun Cheng, Haowen Wang +5
Recent advances in Vision-Language-Action (VLA) and world-model methods have improved generalization in tasks such as robotic manipulation and object interaction. However, Successf…
PersonaLedger: Generating Realistic Financial Transactions with Persona Conditioned LLMs and Rule Grounded Feedback
Dehao Yuan, Tyler Farnan, Stefan Tesliuc +8
Strict privacy regulations limit access to real transaction data, slowing open research in financial AI. Synthetic data can bridge this gap, but existing generators do not jointly…
Evaluating Parameter Efficient Methods for RLVR
Qingyu Yin, Yulun Wu, Zhennan Shen +6
We systematically evaluate Parameter-Efficient Fine-Tuning (PEFT) methods under the paradigm of Reinforcement Learning with Verifiable Rewards (RLVR). RLVR incentivizes language mo…
AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs
David McCoy, Yulun Wu, Zachary Butzin-Dozier
This position paper challenges the "scaling fundamentalism" dominating AI research, where unbounded growth in model size and computation has led to unsustainable environmental impa…