Skip to content

Author

Feng Zhu

We have 2 of 47 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference Open access Aug 2026

Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning Inference

In simulation-in-the-loop decision-making systems, reinforcement learning (RL) inference is often constrained by simulator-side execution overhead, where workloads are highly dynamic and sensitive to runtime thread configurations. Existing multithreaded strategies struggle to match thread resources before or during exe...

Ji-Ming Su, Han-Tao Hua, Lu-Jia Yin et al. · 0 citations
Conference Open access Sep 2026

Grammar-State Aware Beam Search for Enhancing Structural Diversity in LLM Generation

GSA-Beam improves explicit state coverage and final structural diversity while preserving schema validity while preserving schema validity; across several LLM backbones, it reduces reference latency by 22.5% on average compared with standard constrained beam search.

Han-Tao Hua, Ji-Ming Su, Yi-Ping Yao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.