Showing 1–15 of 15 results
/ Date/ Name
Nov 18, 2022Path Independent Equilibrium Models Can Better Exploit Test-Time ComputationJul 11, 2022Exploring Length Generalization in Large Language ModelsAug 27, 2021Learning to Give Checkable Answers with Prover-Verifier GamesJun 20, 2024Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training DataJan 31, 2025Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingAug 5, 2021Learning to ElectOct 28, 2024Sabotage Evaluations for Frontier ModelsAug 7, 2023Studying Large Language Model Generalization with Influence FunctionsNov 3, 2019Preventing Gradient Attenuation in Lipschitz Constrained Convolutional NetworksDec 5, 2025Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMsJun 29, 2022Solving Quantitative Reasoning Problems with Language ModelsNov 13, 2018Sorting out Lipschitz function approximationNov 22, 2018TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre TransferJan 10, 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingApr 18, 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization