3

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
Vision-Language Models (VLMs) have demonstrated remarkable success across diverse visual tasks, yet their performance degrades in …
Yuyao Ge 葛钰峣, Shenghua Liu, Yiwei Wang, Lingrui Mei, Baolong Bi, Xuanshan Zhou, Jiayu Yao, Jiafeng Guo, Xueqi Cheng
PDF Cite DOI arXiv Hugging Face PaperWeekly
Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
Abstract: Prompt-based adversarial attacks have become an effective means to assess the robustness of large language models (LLMs). However, existing approaches often treat prompts as monolithic text, overlooking their structural heterogeneity-different prompt components contribute unequally to adversarial robustness.
Yujia Zheng, Tianhao Li, Haotian Huang, Tianyu Zeng, Jingyu Lu, Chuangxin Chu, Yuekai Huang, Ziyou Jiang, Qian Xiong, Yuyao Ge 葛钰峣, Mingyang Li
Aug 3, 2025
PDF Cite DOI arXiv
Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
A Survey of Context Engineering for Large Language Models
The performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. …
Lingrui Mei, Jiayu Yao, Yuyao Ge 葛钰峣, Yiwei Wang, Baolong Bi, Yujun Cai, Jiazhi Liu, Mingyu Li, Zhong-Zhi Li, Duzhen Zhang, Chenlin Zhou, Jiayi Mao, Tianze Xia, Jiafeng Guo, Shenghua Liu
PDF Cite Code DOI arXiV Hugging Face
A Survey of Context Engineering for Large Language Models
PIS:Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression
Abstract: Large language models (LLMs) have achieved remarkable progress, demonstrating unprecedented capabilities across various natural language processing tasks. However, the high costs associated with such exceptional performance limit the widespread adoption of LLMs, highlighting the need for prompt compression.
Lizhe Chen, Binjia Zhou, Yuyao Ge 葛钰峣, Jiayi Chen, Shiguang Ni
Apr 23, 2025
PDF Cite DOI arXiv
PIS:Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression
a1: Steep Test-time Scaling Law via Environment Augmented Generation
Large Language Models (LLMs) have made remarkable breakthroughs in reasoning, yet continue to struggle with hallucinations, logical …
Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Yuyao Ge 葛钰峣, Jun Wan, Yurong Wu, Xueqi Cheng
Apr 20, 2025
PDF Cite DOI
a1: Steep Test-time Scaling Law via Environment Augmented Generation
Innate Reasoning is Not Enough : In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
TBD
Yuyao Ge 葛钰峣, Shenghua Liu, Yiwei Wang, Lingrui Mei, Lizhe Chen, Baolong Bi, Xueqi Cheng
PDF Cite DOI arXiv Hugging Face
Innate Reasoning is Not Enough : In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking