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

Haoyang Li

7 indexed papers

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

Publications per year

7
26

Top categories

AI×3Crypto×2Robotics×2NLP×2Complexity×1Vision×1Distributed×1

Frequent co-authors

Jie Zhang3×
Anzhe Chen3×
Gengze Zhou3×
Hang Yin3×
Haoqi Yuan3×
Jiazhao Zhang3×

Research Timeline

2026
Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions

This paper proposes a comprehensive taxonomy (SLOT) to systematically categorize security risks, attacks, and defenses specific to Retrieval-Augmented Generation (RAG), clarifying that these risks are distinct from inherent LLM flaws.

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic tasks and embodiments.

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic tasks and embodiments.

Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-training

ForeMoE is a load balancing system for Mixture-of-Experts reinforcement learning post-training that achieves up to a 1.45x speedup.

Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation

Qwen-RobotWorld is a language-conditioned video world model for embodied intelligence that predicts physically grounded future visual trajectories.

The Complexity of Auditing Disclosure-Robust Defeasible Explanations

This paper studies the robustness of formal explanations under incremental disclosure.

From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs

This paper reveals a new vulnerability in Language Model (LLM) inference efficiency caused by persona consistency and proposes RolePlay, a framework to amplify inference costs.

Highlighted terms show continued research focus across papers

Papers

cs.CREmpiricalRecentJul 28, 2026

From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs

Zhiyi Mou, Wangze Ni, Tianfang Xiao, Haoyang LI +5 more

This paper reveals a new vulnerability in Language Model (LLM) inference efficiency caused by persona consistency and proposes RolePlay, a framework to amplify inference costs.

View →
cs.CCTheoreticalRecent
Jun 17, 2026

The Complexity of Auditing Disclosure-Robust Defeasible Explanations

Haoyang Li

This paper studies the robustness of formal explanations under incremental disclosure.

View →
cs.CVEmpiricalRecentJun 15, 2026

Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation

Jie Zhang, Xiaoyue Chen, Anzhe Chen, Chenxu Lv +34 more

Qwen-RobotWorld is a language-conditioned video world model for embodied intelligence that predicts physically grounded future visual trajectories.

View →
cs.DCEmpiricalRecentJun 10, 2026

Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-training

Yuming Zhou, Haoyang Li, Sheng Lin, Yanfeng Zhao +5 more

ForeMoE is a load balancing system for Mixture-of-Experts reinforcement learning post-training that achieves up to a 1.45x speedup.

View →
cs.ROcs.AIcs.CLRecentMay 28, 2026

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Qiuyue Wang, Mingsheng Li, Jian Guan, Jinhui Ye +36 more

Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic ta…

View →
cs.ROcs.AIcs.CLRecentMay 28, 2026

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Qiuyue Wang, Mingsheng Li, Jian Guan, Jinhui Ye +36 more

Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic ta…

View →
cs.CRcs.AIApr 9, 2026

Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions

Yuming Xu, Mingtao Zhang, Zhuohan Ge, Haoyang Li +6 more

This paper proposes a comprehensive taxonomy (SLOT) to systematically categorize security risks, attacks, and defenses specific to Retrieval-Augmented Generation (RAG), clarifying that these risks are…

View →