-
Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective
Paper • 2502.17262 • Published • 22 -
MAGA: MAssive Genre-Audience Reformulation to Pretraining Corpus Expansion
Paper • 2502.04235 • Published • 22 -
AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection
Paper • 2505.07293 • Published • 27
shenke
shenke18
AI & ML interests
None yet
Organizations
-
Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective
Paper • 2502.17262 • Published • 22 -
MAGA: MAssive Genre-Audience Reformulation to Pretraining Corpus Expansion
Paper • 2502.04235 • Published • 22 -
AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection
Paper • 2505.07293 • Published • 27
models
0
None public yet
datasets
0
None public yet