4 papers · 1 filter
FAMOSE: A ReAct Approach to Automated Feature Discovery
Keith Burghardt, Jienan Liu, Sadman Sakib +2
Feature engineering remains a critical yet challenging bottleneck in machine learning, particularly for tabular data, as identifying optimal features from an exponentially large fe…
Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients
Yezhen Wang, Zhouhao Yang, Brian K Chen +4
Building upon the success of low-rank adapter (LoRA), low-rank gradient projection (LoRP) has emerged as a promising solution for memory-efficient fine-tuning. However, existing Lo…
Anyprefer: An Agentic Framework for Preference Data Synthesis
Yiyang Zhou, Zhaoyang Wang, Tianle Wang +13
High-quality preference data is essential for aligning foundation models with human values through preference learning. However, manual annotation of such data is often time-consum…
ControllableGPT: A Ground-Up Designed Controllable GPT for Molecule Optimization
Xuefeng Liu, Songhao Jiang, Bo Li +1
Large Language Models (LLMs) employ three popular training approaches: Masked Language Models (MLM), Causal Language Models (CLM), and Sequence-to-Sequence Models (seq2seq). Howeve…