3 papers
cs.CL2026
Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training
Changhao Jiang, Ming Zhang, Yifei Cao +12
The GPT-4 technical report suggests that downstream performance can be predicted from pre-training signals, but offers little methodological detail on how to quantify this. This wo…
nucl-th2025
Directly probing existence of -cluster structure in Ne by relativistic heavy-ion collisions
Lu-Meng Liu, Hai-Cheng Wang, Song-Jie Li +5
Can relativistic heavy-ion collisions only probe the global shape of colliding nuclei, or their detailed internal structure as well? Taking Ne as an example, we attempt to d…
nucl-th2024
Probing configuration of clusters with spectator particles in relativistic heavy-ion collisions
Lu-Meng Liu, Song-Jie Li, Zhen Wang +3
We propose to use spectator particle yield ratios to probe the configuration of clusters in C and O by their collisions at RHIC and LHC energies. The idea is ill…