Viacheslav Sinii

model compression (1) reinforcement learning (1) multi-task learning (1) few-shot learning (1) mathematical reasoning (1) chain-of-thought reasoning (1) scalable training (1) adaptive agent (1) meta-reinforcement learning (1) task distribution (1) reinforcement learning benchmark (1) scalable computing (1) multi-task adaptation (1) steering vector (1) gradient-based meta-learning (1) environment simulation (1) bias-only adaptation (1) environment benchmarking (1) logit-lens analysis (1) scalable environment (1)