4 papers
When Model Merging Rivals Joint Multi-Task Reinforcement Learning: A Task-Vector Geometry Analysis
S. Aaron McClendon
Model merging is promoted as a substitute for joint multi-task training, yet in the reinforcement-learning setting this substitution is essentially never tested against the baselin…
Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents
S. Aaron McClendon, Jorge Gallego-Feliciano, Stavros Zervoudakis +1
Large language model (LLM) agents show promise on realistic tool-use tasks, but deploying capable agents on modest hardware remains challenging. We study whether inference-time sca…
Hidden Dynamics of Massive Activations in Transformer Training
Jorge Gallego-Feliciano, S. Aaron McClendon, Juan Morinelli +2
We present the first comprehensive analysis of massive activation development throughout transformer training, using the Pythia model family as our testbed, and release our full da…
Reinforcement Learning for Machine Learning Model Deployment: Evaluating Multi-Armed Bandits in ML Ops Environments
S. Aaron McClendon, Vishaal Venkatesh, Juan Morinelli
In modern ML Ops environments, model deployment is a critical process that traditionally relies on static heuristics such as validation error comparisons and A/B testing. However,…