Shangshang Wang is a CS PhD student at USC, advised by Willie Neiswanger. Shangshang received the Master's and Bachelor's degrees from ShanghaiTech. Shangshang centers on reinforcement learning (RL), large language models (LLMs), agents and foundation models.

[email protected] · X · LinkedIn · Instagram · RedNote

Experience

Research Intern · Stealth AI Startup · 2026

• Some RL, some LLMs, and some agents.

Research Intern · Qwen · 2026

• Stable and efficient agentic RL post-training for LLMs.
• Hosts: Guoyin Wang (Qwen Pilot Team)

Research Intern · Bespoke Labs · 2025

• Agentic RL post-training acceleration via reward / environment curation.
• Hosts: Mahesh Sathiamoorthy, Alex Dimakis, and Greg Durrett

Selected Publications

The full list of publications is at Scholar

LLMs

• Tina: Tiny Reasoning Models via LoRA. ICLR 2026. Shangshang Wang, Julian Asilis, Ömer Faruk Akgül, Enes Burak Bilgin, Ollie Liu, Willie Neiswanger. paper · web · code · HF · X
• Resa: Transparent Reasoning Models via SAEs. COLM 2026. Shangshang Wang, Julian Asilis, Ömer Faruk Akgül, Enes Burak Bilgin, Ollie Liu, Deqing Fu, Willie Neiswanger. paper · web · code · HF · X
• FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization. COLM 2026 **Chiyu Ma, Shuo Yang, Kexin Huang, Jinda Lu, Haoming Meng, Shangshang Wang, Bolin Ding, Soroush Vosoughi, Guoyin Wang, Jingren Zhou. paper · web · code · HF

Foundation Models