Suchergebnisse - Sam, Dylan

Predicting the Performance of Black-box LLMs through Follow-up Queries von Sam, Dylan, Finzi, Marc, Kolter, J. Zico

Volltext

Finetuning CLIP to Reason about Pairwise Differences von Sam, Dylan, Willmott, Devin, Semedo, Joao D., Kolter, J. Zico

Volltext

Auditing Fairness under Unobserved Confounding von Byun, Yewon, Sam, Dylan, Oberst, Michael, Lipton, Zachary C., Wilder, Bryan

Volltext

Evaluating Language Model Reasoning about Confidential Information von Sam, Dylan, Robey, Alexander, Zou, Andy, Fredrikson, Matt, Kolter, J. Zico

Volltext

When Should We Introduce Safety Interventions During Pretraining? von Sam, Dylan, Goyal, Sachin, Maini, Pratyush, Robey, Alexander, Kolter, J. Zico

Volltext

Bayesian Neural Networks with Domain Knowledge Priors von Sam, Dylan, Pukdee, Rattana, Jeong, Daniel P., Byun, Yewon, Kolter, J. Zico

Volltext

Analyzing Similarity Metrics for Data Selection for Language Model Pretraining von Sam, Dylan, Chakrabarti, Ayan, Rostamizadeh, Afshin, Ramalingam, Srikumar, Citovsky, Gui, Kumar, Sanjiv

Volltext

Computing Low-Entropy Couplings for Large-Support Distributions von Sokota, Samuel, Sam, Dylan, de Witt, Christian Schroeder, Compton, Spencer, Foerster, Jakob, Kolter, J. Zico

Volltext

Safety Pretraining: Toward the Next Generation of Safe AI von Maini, Pratyush, Goyal, Sachin, Sam, Dylan, Robey, Alex, Savani, Yash, Jiang, Yiding, Zou, Andy, Fredrikson, Matt, Lipton, Zacharcy C., Kolter, J. Zico

Volltext