8 papers
Report for NSF Workshop on AI for Electronic Design Automation
Deming Chen, Vijay Ganesh, Weikai Li +7
This report distills the discussions and recommendations from the NSF Workshop on AI for Electronic Design Automation (EDA), held on December 10, 2024 in Vancouver alongside NeurIP…
Choosing How to Remember: Adaptive Memory Structures for LLM Agents
Mingfei Lu, Mengjia Wu, Feng Liu +8
Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing agent memory systems suffer…
From Newborn to Impact: Bias-Aware Citation Prediction
Mingfei Lu, Mengjia Wu, Jiawei Xu +6
As a key to accessing research impact, citation dynamics underpins research evaluation, scholarly recommendation, and the study of knowledge diffusion. Citation prediction is parti…
Multimodal LLM With Hierarchical Mixture-of-Experts for VQA on 3D Brain MRI
Arvind Murari Vepa, Yannan Yu, Jingru Gan +6
Multiparametric 3D brain MRI (mpMRI) is central to neuroradiology, but producing tumor location, appearance, size, and involvement of critical structures for neurosurgical planning…
How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
Hongzhe Du, Weikai Li, Min Cai +5
Post-training is essential for the success of large language models (LLMs), transforming pre-trained base models into more useful and aligned post-trained models. While plenty of w…
Iceberg: Enhancing HLS Modeling with Synthetic Data
Zijian Ding, Tung Nguyen, Weikai Li +3
Deep learning-based prediction models for High-Level Synthesis (HLS) of hardware designs often struggle to generalize. In this paper, we study how to close the generalizability gap…