2 papers
cs.LG2026
Bug or Feature: Weight Drift, Activation Sparsity and Spikes
Egor Shvetsov, Aleksandr Serkov, Shokorov Viacheslav +3
The design of modern neural architectures has converged through incremental empirical choices, yet the mechanisms governing their training dynamics remain only partially understood…
cs.LG2026
Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner
Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin +11
Recent progress in in-context reinforcement learning (ICRL) has demonstrated its potential for training generalist agents that can acquire new tasks directly at inference. Algorith…