Brian R. Bartoldson

A Comedy of Estimators: On KL Regularization in RL Training of LLMs

Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence

Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security

Scalable Pretraining of Retrieval Models

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training

ELFS: Label-Free Coreset Selection with Proxy Training Dynamics

Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness

Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts