Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
How Implicit Bias Accumulates and Propagates in LLM Long-term Memory
Yiming Ma, Lixu Wang, Lionel Z. Wang +6
Long-term memory mechanisms enable Large Language Models (LLMs) to maintain continuity and personalization across extended interaction lifecycles, but they also introduce new and u…
cs.LG2025
Sub-Clustering for Class Distance Recalculation in Long-Tailed Drug Classification
Yujia Su, Xinjie Li, Lionel Z. Wang
In the real world, long-tailed data distributions are prevalent, making it challenging for models to effectively learn and classify tail classes. However, we discover that in the f…
cs.LG2024
Modeling Inverse Ellipsometry Problem via Flow Matching with a Large-Scale Dataset
Yiming Ma, Jianzhi Teng, Xinjie Li +5
Inverse ellipsometry, i.e., reconstructing optical constants and film thickness from the measured phase difference and amplitude ratio , is a fundamentally ill-posed problem…