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
published a Space 1 day ago
obversarystudios/deepseek-ai-DeepSeek-V4-Pro liked a model 1 day ago
deepseek-ai/DeepSeek-V4-Pro upvoted an article 1 day ago
DeepSeek-V4: a million-token context that agents can actually useOrganizations
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 • 94 -
Normalizing Trajectory Models
Paper • 2605.08078 • Published • 14 -
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 • 94 -
Normalizing Trajectory Models
Paper • 2605.08078 • Published • 14 -
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
Paper • 2605.08029 • Published • 10