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

Meng Sun

5 indexed papers

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

Publications per year

5
26

Top categories

Vision×3AI×3NLP×2Crypto×2HCI×1Info Retrieval×1ML×1

Frequent co-authors

Yihao Zhang2×
Shenghui Chen1×
Po-han Li1×
Ximeng Sun1×
Shijia Yang1×
Emad Barsoum1×

Research Timeline

2026
The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems

The paper introduces Salami Slicing Risk, a novel multi-turn jailbreak technique that accumulates harmful intent through numerous low-risk inputs, achieving state-of-the-art attack success rates against major LLMs.

VOW: Verifiable and Oblivious Watermark Detection for Large Language Models

VOW introduces a novel, privacy-preserving, and cryptographically verifiable protocol for detecting watermarks in LLM-generated text, overcoming the limitations of centralized and non-verifiable existing methods.

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

The paper introduces Harness-1, a search agent that separates semantic decision-making from state management by using a stateful search harness, achieving state-of-the-art performance across diverse retrieval benchmarks.

MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation

This paper introduces MonoIR-RS, a large-scale infrared remote-sensing vision-language dataset and benchmark for understanding infrared imagery.

VEGAS: Human-Aligned Video Caption Evaluation via Gaze

The paper proposes VEGAS, a metric for video captioning that uses test-time gaze to sample personalized captions aligning with human focus.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIcs.HCEmpiricalRecentJul 9, 2026

VEGAS: Human-Aligned Video Caption Evaluation via Gaze

Shenghui Chen, Po-han Li, Ximeng Sun, Shijia Yang +4 more

The paper proposes VEGAS, a metric for video captioning that uses test-time gaze to sample personalized captions aligning with human focus.

View →
cs.CVDatasetRecent
Jul 7, 2026

MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation

Jiaju Han, Ma Yaqi, Yahui Chai, Xuemeng Sun +7 more

This paper introduces MonoIR-RS, a large-scale infrared remote-sensing vision-language dataset and benchmark for understanding infrared imagery.

View →
cs.AIcs.CLcs.IRRecentJun 1, 2026

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

Pengcheng Jiang, Zhiyi Shi, Kelly Hong, Xueqiang Xu +4 more

The paper introduces Harness-1, a search agent that separates semantic decision-making from state management by using a stateful search harness, achieving state-of-the-art performance across diverse r…

View →
cs.CRRecentApr 30, 2026

VOW: Verifiable and Oblivious Watermark Detection for Large Language Models

Xiaokun Luan, Yihao Zhang, Pengcheng Su, Feiran Lei +1 more

VOW introduces a novel, privacy-preserving, and cryptographically verifiable protocol for detecting watermarks in LLM-generated text, overcoming the limitations of centralized and non-verifiable exist…

View →
cs.CRcs.AIcs.CLRecentApr 13, 2026

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems

Yihao Zhang, Kai Wang, Jiangrong Wu, Haolin Wu +6 more

The paper introduces Salami Slicing Risk, a novel multi-turn jailbreak technique that accumulates harmful intent through numerous low-risk inputs, achieving state-of-the-art attack success rates again…

View →