PPL
Mihir Parmar
Papers (6)
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-EvidenceLiSA: Lifelong Safety Adaptation via Conservative Policy InductionNexus : An Agentic Framework for Time Series ForecastingLEAF: A Living Benchmark for Event-Augmented ForecastingReasoning-Aware Training for Time Series ForecastingMid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models