Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Zhongxiang Dai

Zhongxiang Dai

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

NLP×2AI×1ML×1

Frequent co-authors

Kaiyu Huang1×
Xingyu Wang1×
Mingze Kong1×
Zhubo Shi1×
Yuqian Hou1×
Hong Xu1×

Research Timeline

2026
UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling

UniScale proposes a unified framework that jointly optimizes model routing and test-time scaling to achieve a superior, fine-grained quality-cost trade-off for large language model inference.

DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization

DRIFT proposes a novel framework that efficiently optimizes LLMs for multi-turn interactions by decoupling rollout from optimization, allowing the use of weighted supervised fine-tuning to match the performance of expensive online reinforcement learning.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CLRecentMay 29, 2026

UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling

Kaiyu Huang, Xingyu Wang, Mingze Kong, Zhubo Shi +5 more

UniScale proposes a unified framework that jointly optimizes model routing and test-time scaling to achieve a superior, fine-grained quality-cost trade-off for large language model inference.

View →
cs.LGcs.CLRecentMay 29, 2026

DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization

Jian Mu, Tianyi Lin, Chengwei Qin, Zhongxiang Dai +1 more

DRIFT proposes a novel framework that efficiently optimizes LLMs for multi-turn interactions by decoupling rollout from optimization, allowing the use of weighted supervised fine-tuning to match the p…

View →