2025 Poster "linear classifiers" Papers
2 papers found
Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
Yunzhen Feng, Elvis Dohmatob, Pu Yang et al.
ICLR 2025posterarXiv:2406.07515
Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
Haiyan Zhao, Heng Zhao, Bo Shen et al.
ICLR 2025posterarXiv:2410.00153
16
citations