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

Bin Cui

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

ML×2AI×2Architecture×1NLP×1

Frequent co-authors

Xupeng Miao3×
Chunan Shi1×
Yilei Chen1×
Yilin Chen1×
Weitong Qian1×
Beicheng Xu1×

Research Timeline

2026
AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle

AutoSci is a memory-centric agentic system designed to automate the entire scientific research lifecycle by integrating structured memory, multi-stage execution, and continuous self-improvement.

DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning

The paper proposes DARTS, a distribution-aware active rollout trajectory shaping method that fundamentally accelerates LLM reinforcement learning by actively shaping the long-tail response distribution towards conciseness and certainty.

Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving

The paper proposes AsymCache, a computation-latency-aware KV cache management system that optimizes LLM inference by aligning cache eviction decisions with GPU attention kernel performance, significantly reducing both Time-to-First-Token (TTFT) and Time-Per-Output-Token (TPOT).

Highlighted terms show continued research focus across papers

Papers

cs.ARcs.CLcs.LGRecentJun 1, 2026

Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving

Chunan Shi, Yilei Chen, Yilin Chen, Xupeng Miao +1 more

The paper proposes AsymCache, a computation-latency-aware KV cache management system that optimizes LLM inference by aligning cache eviction decisions with GPU attention kernel performance, significan…

View →
cs.AIRecentMay 29, 2026

AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle

Weitong Qian, Beicheng Xu, Zhongao Xie, Bowen Fan +15 more

AutoSci is a memory-centric agentic system designed to automate the entire scientific research lifecycle by integrating structured memory, multi-stage execution, and continuous self-improvement.

View →
cs.LGcs.AIRecentMay 29, 2026

DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning

Yujie Wang, Siwei Chen, Longzan Luo, Xinyi Liu +3 more

The paper proposes DARTS, a distribution-aware active rollout trajectory shaping method that fundamentally accelerates LLM reinforcement learning by actively shaping the long-tail response distributio…

View →