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

Jian Yang

6 indexed papers

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

Publications per year

6
26

Top categories

AI×4Crypto×2NLP×2ML×1Databases×1Info Retrieval×1

Frequent co-authors

Xianglong Liu2×
Yuan Tong1×
Qinbin Li1×
Zeyi Wen1×
Xiaofang Zhou1×
Xudong Zhang1×

Research Timeline

2026
AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization

AgentVisor is a novel defense framework that uses semantic virtualization, inspired by OS principles, to significantly reduce LLM agent vulnerability to prompt injection while maintaining high utility.

MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection

MIRA proposes a novel source-aware filtering framework that discovers and anchors evaluation rubrics during data selection, significantly improving code-oriented mid-training data quality while reducing token usage.

Rubric-Guided Process Reward for Stepwise Model Routing

The paper proposes RoRo, a rubric-guided process reward framework that improves stepwise model routing by evaluating the quality of intermediate reasoning steps, leading to better performance and cost trade-offs.

The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning

The paper proposes a dual-interventional framework to characterize how linguistic structures and contextual cues influence LLMs' spatial reasoning for navigation, finding that topological information is crucial, while semantic details can be unreliable.

Vector Linking via Cross-Model Local Isometric Consistency

The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small set of paired anchors.

Preserving Data Privacy in Learning Causal Structure with Fully Homomorphic Encryption

The paper proposes a novel method using fully homomorphic encryption (FHE) to learn causal structures while preserving data privacy, achieving high consistency and practical efficiency.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.LGRecentJun 3, 2026

Preserving Data Privacy in Learning Causal Structure with Fully Homomorphic Encryption

Jian Yang, Yuan Tong, Qinbin Li, Zeyi Wen +1 more

The paper proposes a novel method using fully homomorphic encryption (FHE) to learn causal structures while preserving data privacy, achieving high consistency and practical efficiency.

View →
cs.CLcs.AIRecentMay 29, 2026

The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning

Xudong Zhang, Jian Yang, Shengkai Wang, Jiangpeng Tian +4 more

The paper proposes a dual-interventional framework to characterize how linguistic structures and contextual cues influence LLMs' spatial reasoning for navigation, finding that topological information…

View →
cs.AIcs.DBcs.IRRecentMay 29, 2026

Vector Linking via Cross-Model Local Isometric Consistency

Ziying Chen, Yang Cao, He Sun, Beining Yang +1 more

The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…

View →
cs.AIRecentMay 28, 2026

MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection

Haowen Wang, Yaxin Du, Jian Yang, Jiajun Wu +8 more

MIRA proposes a novel source-aware filtering framework that discovers and anchors evaluation rubrics during data selection, significantly improving code-oriented mid-training data quality while reduci…

View →
cs.AIcs.CLRecentMay 28, 2026

Rubric-Guided Process Reward for Stepwise Model Routing

Shenghao Ye, Yu Guo, Zhengheng Li, Shuangwu Chen +1 more

The paper proposes RoRo, a rubric-guided process reward framework that improves stepwise model routing by evaluating the quality of intermediate reasoning steps, leading to better performance and cost…

View →
cs.CRRecentApr 27, 2026

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization

Zonghao Ying, Haozheng Wang, Jiangfan Liu, Quanchen Zou +4 more

AgentVisor is a novel defense framework that uses semantic virtualization, inspired by OS principles, to significantly reduce LLM agent vulnerability to prompt injection while maintaining high utility…

View →