Sam, Dylan

16 publications

NeurIPS 2025 Analyzing Similarity Metrics for Data Selection for Language Model Pretraining Dylan Sam, Ayan Chakrabarti, Afshin Rostamizadeh, Srikumar Ramalingam, Gui Citovsky, Sanjiv Kumar

TMLR 2025 Finetuning CLIP to Reason About Pairwise Differences Dylan Sam, Devin Willmott, João D. Semedo, J Zico Kolter

NeurIPS 2025 Predicting the Performance of Black-Box Language Models with Follow-up Queries Dylan Sam, Marc Anton Finzi, J Zico Kolter

NeurIPS 2025 Safety Pretraining: Toward the Next Generation of Safe AI Pratyush Maini, Sachin Goyal, Dylan Sam, Alexander Robey, Yash Savani, Yiding Jiang, Andy Zou, Matt Fredrikson, Zachary Chase Lipton, J Zico Kolter

AISTATS 2024 Auditing Fairness Under Unobserved Confounding Yewon Byun, Dylan Sam, Michael Oberst, Zachary Lipton, Bryan Wilder

UAI 2024 Computing Low-Entropy Couplings for Large-Support Distributions Samuel Sokota, Dylan Sam, Christian Witt, Spencer Compton, Jakob Foerster, J. Zico Kolter

ICMLW 2024 Eliciting Black-Box Representations from LLMs Through Self-Queries Dylan Sam, Marc Anton Finzi

ICLR 2024 Understanding Prompt Engineering May Not Require Rethinking Generalization Victor Akinwande, Yiding Jiang, Dylan Sam, J Zico Kolter

ICMLW 2023 Identifying Inequity in Treatment Allocation Yewon Byun, Dylan Sam, Zachary Chase Lipton, Bryan Wilder

ICLR 2023 Label Propagation with Weak Supervision Rattana Pukdee, Dylan Sam, Pradeep Kumar Ravikumar, Nina Balcan

NeurIPS 2023 Learning with Explanation Constraints Rattana Pukdee, Dylan Sam, J. Zico Kolter, Maria-Florina F Balcan, Pradeep K. Ravikumar

ICLRW 2023 Learning with Explanation Constraints Rattana Pukdee, Dylan Sam, J Zico Kolter, Nina Balcan, Pradeep Kumar Ravikumar

AAAI 2023 Losses over Labels: Weakly Supervised Learning via Direct Loss Construction Dylan Sam, J. Zico Kolter

ICMLW 2023 Understanding Prompt Engineering Does Not Require Rethinking Generalization Victor Akinwande, Yiding Jiang, Dylan Sam, J Zico Kolter

AISTATS 2021 Semi-Supervised Aggregation of Dependent Weak Supervision Sources with Performance Guarantees Alessio Mazzetto, Dylan Sam, Andrew Park, Eli Upfal, Stephen Bach

ICML 2021 Adversarial Multi Class Learning Under Weak Supervision with Performance Guarantees Alessio Mazzetto, Cyrus Cousins, Dylan Sam, Stephen H Bach, Eli Upfal