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

Yu Song

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

AI×3Info Retrieval×2Crypto×2NLP×1Multiagent×1Vision×1ML×1Robotics×1

Frequent co-authors

Ziyu Song1×
Jiaming Fang1×
Kuangyu Li1×
Tuo Xia1×
Chuanpeng Wang1×
Yuecheng Li1×

Research Timeline

2026
Natural Language based Specification and Verification

This paper proposes using large language models (LLMs) to generate and compositionally verify software implementations directly from natural language specifications, showing promising preliminary results.

Systematic Discovery of Semantic Attacks in Online Map Construction through Conditional Diffusion

The paper introduces MIRAGE, a framework that systematically discovers semantic attacks on online HD map construction by finding plausible environmental variations that bypass standard adversarial defenses, demonstrating attacks that remove or inject critical road boundaries.

AgentSchool: An LLM-Powered Multi-Agent Simulation for Education

The paper introduces AgentSchool, an advanced LLM-powered multi-agent simulator that models learning as state transitions to provide a robust, ethically viable testbed for educational research and pedagogical reform.

Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation

Taiji is a novel LLM-as-Enhancer framework that optimizes recommender systems by addressing the challenges of generating high-quality reasoning data and balancing semantic and ID-based rewards.

Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation

This paper proposes Tail-Aware Adaptive-k (TAA-k), a training-free framework for adaptive context selection in retrieval-augmented generation systems using Extreme Value Theory.

Highlighted terms show continued research focus across papers

Papers

cs.IREmpiricalRecentJun 10, 2026

Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation

Ziyu Song, Jiaming Fang, Kuangyu Li, Tuo Xia +1 more

This paper proposes Tail-Aware Adaptive-k (TAA-k), a training-free framework for adaptive context selection in retrieval-augmented generation systems using Extreme Value Theory.

View →
cs.IRcs.AIcs.CLRecent
Jun 2, 2026

Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation

Yuecheng Li, Zeyu Song, Jing Yao, Chi Lu +2 more

Taiji is a novel LLM-as-Enhancer framework that optimizes recommender systems by addressing the challenges of generating high-quality reasoning data and balancing semantic and ID-based rewards.

View →
cs.AIcs.MARecentMay 28, 2026

AgentSchool: An LLM-Powered Multi-Agent Simulation for Education

Yulei Ye, Wenhao Li, Zhong Wen, Yunshu Huang +22 more

The paper introduces AgentSchool, an advanced LLM-powered multi-agent simulator that models learning as state transitions to provide a robust, ethically viable testbed for educational research and ped…

View →
cs.CVcs.CRcs.LGRecentMay 14, 2026

Systematic Discovery of Semantic Attacks in Online Map Construction through Conditional Diffusion

Chenyi Wang, Ruoyu Song, Raymond Muller, Jean-Philippe Monteuuis +4 more

The paper introduces MIRAGE, a framework that systematically discovers semantic attacks on online HD map construction by finding plausible environmental variations that bypass standard adversarial def…

View →
cs.SEcs.AIcs.CRRecentMay 11, 2026

Natural Language based Specification and Verification

Zhaorui Li, Chengyu Song

This paper proposes using large language models (LLMs) to generate and compositionally verify software implementations directly from natural language specifications, showing promising preliminary resu…

View →