Hongyu H

The paper introduces a quotient-DAG view to accurately estimate unordered slate propensities for off-policy evaluation, solving the nuisance variance and computational gap inherent in standard importance sampling for autoregressive recommenders.

SIRI introduces a self-internalizing reinforcement learning framework that allows LLM agents to autonomously discover and integrate reusable skills directly into their core policy, significantly improving performance on complex tasks without external skill generators.

This paper presents TypoNet, a system that constructs and validates a symbolic model of a production-scale WAN from network artifacts using large language models for translation and a solver for reliable long-horizon reasoning.

This paper proposes a system called Autogram that uses AI and statistics to discover and validate network invariants.