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

Tianlong Chen

6 indexed papers

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

Publications per year

6
26

Top categories

AI×5ML×4Info Retrieval×3NLP×3Crypto×2

Frequent co-authors

Yuhang Chen3×
Mingfu Liang3×
Xiaohan Wei3×
Yunchen Pu3×
Fei Tian3×
Chonglin Sun3×

Research Timeline

2026
Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

This study provides the first large-scale measurement of prompt injection attacks in real-world LLM-based resume screening, finding that approximately 1% of resumes contain hidden injections.

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

This study provides the first systematic measurement of prompt injection attacks in a real-world LLM-based resume screening application, finding that approximately 1% of resumes contain hidden injections.

End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference

This paper proposes Learning to Allocate (L2A), an end-to-end framework for resource-adaptive inference in Large Language Models (LLMs) using budget-conditioned and input-aware gating networks.

Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation

This paper introduces Bifocal dLLMs (R2LM), a new paradigm for discrete diffusion language models that combines causal and bidirectional attention for improved throughput and generation quality.

Generative Skill Composition for LLM Agents

This paper introduces SkillComposer, a method for structured skill composition in LLM agents, which predicts an executable skill plan that jointly specifies the activated subset, count, and execution order.

Diffusion-GR2: Diffusion Generative Reasoning Re-ranker

This paper proposes Diffusion-GR2, a method to convert an autoregressive reasoning re-ranker into a block-diffusion re-ranker while maintaining accuracy and increasing speed.

Highlighted terms show continued research focus across papers

Papers

cs.IRcs.AIEmpiricalRecentJul 1, 2026

Diffusion-GR2: Diffusion Generative Reasoning Re-ranker

Zhuoxuan Zhang, Kangqi Ni, Yuhang Chen, Mingfu Liang +11 more

This paper proposes Diffusion-GR2, a method to convert an autoregressive reasoning re-ranker into a block-diffusion re-ranker while maintaining accuracy and increasing speed.

View →
cs.CLEmpiricalRecent
Jun 30, 2026

Generative Skill Composition for LLM Agents

Xinyu Zhao, Zhen Tan, Vaishnav Tadiparthi, Nakul Agarwal +4 more

This paper introduces SkillComposer, a method for structured skill composition in LLM agents, which predicts an executable skill plan that jointly specifies the activated subset, count, and execution…

View →
cs.IRcs.AIcs.LGEmpiricalRecentJun 26, 2026

End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference

Yuhang Chen, Jinhao Duan, Ruichen Zhang, Mingfu Liang +10 more

This paper proposes Learning to Allocate (L2A), an end-to-end framework for resource-adaptive inference in Large Language Models (LLMs) using budget-conditioned and input-aware gating networks.

View →
cs.IRcs.AIcs.LGEmpiricalRecentJun 26, 2026

Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation

Yuhang Chen, Xianfeng Wu, Jinhao Duan, Mingfu Liang +10 more

This paper introduces Bifocal dLLMs (R2LM), a new paradigm for discrete diffusion language models that combines causal and bidirectional attention for improved throughput and generation quality.

View →
cs.CRcs.AIcs.CLRecentMay 27, 2026

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

Mohan Zhang, Yuqi Jia, Zhen Tan, Steven Jiang +3 more

This study provides the first large-scale measurement of prompt injection attacks in real-world LLM-based resume screening, finding that approximately 1% of resumes contain hidden injections.

View →
cs.CRcs.AIcs.CLRecentMay 27, 2026

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

Mohan Zhang, Yuqi Jia, Zhen Tan, Steven Jiang +3 more

This study provides the first systematic measurement of prompt injection attacks in a real-world LLM-based resume screening application, finding that approximately 1% of resumes contain hidden injecti…

View →