Sewoong Oh

OpenThoughts: Data Recipes for Reasoning Models

Sampling from Your Language Model One Byte at a Time

Spurious Rewards: Rethinking Training Signals in RLVR

Concept-Aware Batch Sampling Improves Language-Image Pretraining

Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch

OML: A Primitive for Reconciling Open Access with Owner Control in AI Model Distribution

SuperBPE: Space Travel for Language Models

Scalable Fingerprinting of Large Language Models

Zeroth-Order Optimization Finds Flat Minima

S4S: Solving for a Fast Diffusion Model Solver

Understanding the Gain from Data Filtering in Multimodal Contrastive Learning

Characterizing the Training Dynamics of Private Fine-tuning with Langevin Diffusion

Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models

A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage

Finite-Time Convergence Rates in Stochastic Stackelberg Games with Smooth Algorithmic Agents

Conformal Reasoning: Uncertainty Estimation in Interactive Environments