Genta Indra Winata
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Momento, a new benchmark that evaluates agentic AI's ability to maintain state and reason across multiple, disconnected sessions, revealing that current agents struggle with integrating stale historical context.
The paper introduces OPD+, a corrected on-policy distillation framework that mathematically proves the bias of standard stop-gradient methods and improves the stability and performance of knowledge transfer from teacher to student models.
Papers
OPD+: Rethinking the Advantage Design for On-Policy Distillation
Hanyang Zhao, Haoxian Chen, Han Lin, Genta Indra Winata +2 more
The paper introduces OPD+, a corrected on-policy distillation framework that mathematically proves the bias of standard stop-gradient methods and improves the stability and performance of knowledge tr…