Brian Moran
obversarystudios
·
AI & ML interests
AI evaluation, agent observability, memory substrates, failure traces, boundary mapping, prompt-injection defense, constrained policy learning, cognitive systems
Recent Activity
upvoted a paper about 5 hours ago
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning updated a collection about 5 hours ago
papers upvoted an article about 5 hours ago
A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and BeyondOrganizations
None yet
-
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
Paper • 2603.12180 • Published • 65 -
Flow-OPD: On-Policy Distillation for Flow Matching Models
Paper • 2605.08063 • Published • 93 -
Normalizing Trajectory Models
Paper • 2605.08078 • Published • 12 -
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
Paper • 2605.08029 • Published • 10
-
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
Paper • 2603.12180 • Published • 65 -
Flow-OPD: On-Policy Distillation for Flow Matching Models
Paper • 2605.08063 • Published • 93 -
Normalizing Trajectory Models
Paper • 2605.08078 • Published • 12 -
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
Paper • 2605.08029 • Published • 10