Skip to content
conftrace_

linearization

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

liger attention (1) transformer-based llms (1) bayesian uncertainty quantification (1) currying (1) cryptographically secure data (1) low-rank adaptation (lora) (1) gated recurrent structures (1) key matrix weights (1) accuracy (1) large language model (1)

Papers

FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain ICML 2025 Liger: Linearizing Large Language Models to Gated Recurrent Structures ICML 2025 Linearization Turns Neural Operators into Function-Valued Gaussian Processes ICML 2025 Disparate Impact on Group Accuracy of Linearization for Private Inference ICML 2024