PPL
Michel Galley
Papers (6)
DialoGPT: Large-Scale Generative Pre-training for Conversational Response GenerationDo Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?Test-Time Learning with an Evolving LibrarySkillGen: Verified Inference-Time Agent Skill SynthesisMeasuring and Mitigating the Distributional Gap Between Real and Simulated User BehaviorsAgentic-imodels: Evolving agentic interpretability tools via autoresearch