Trojan Prompt Attacks on Graph Neural Networks

Kavli Affiliate: Xiang Zhang | First 5 Authors: Minhua Lin, Zhiwei Zhang, Enyan Dai, Zongyu Wu, Yilong Wang | Summary: Graph Prompt Learning (GPL) has been introduced as a promising approach that uses prompts to adapt pre-trained GNN models to specific downstream tasks without requiring fine-tuning of the entire model. Despite the advantages of GPL, […]


Continue.. Trojan Prompt Attacks on Graph Neural Networks

NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models

Kavli Affiliate: Xiang Zhang | First 5 Authors: Han Han, Tong Zhu, Xiang Zhang, Mengsong Wu, Hao Xiong | Summary: Large language models (LLMs) combined with tool learning have gained impressive results in real-world applications. During tool learning, LLMs may call multiple tools in nested orders, where the latter tool call may take the former […]


Continue.. NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models

Causal Image Modeling for Efficient Visual Understanding

Kavli Affiliate: Feng Wang | First 5 Authors: Feng Wang, Timing Yang, Yaodong Yu, Sucheng Ren, Guoyizhe Wei | Summary: In this work, we present a comprehensive analysis of causal image modeling and introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual […]


Continue.. Causal Image Modeling for Efficient Visual Understanding

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

Kavli Affiliate: Feng Wang | First 5 Authors: Feng Wang, Timing Yang, Yaodong Yu, Sucheng Ren, Guoyizhe Wei | Summary: In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representations. This modeling paradigm allows us to process images […]


Continue.. Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

Kavli Affiliate: Feng Wang | First 5 Authors: Feng Wang, Timing Yang, Yaodong Yu, Sucheng Ren, Guoyizhe Wei | Summary: In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representations. This modeling paradigm allows us to process images […]


Continue.. Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

Ion-Assisted Nanoscale Material Engineering in Atomic Layers

Kavli Affiliate: Xiang Zhang | First 5 Authors: Hossein Taghinejad, Mohammad Taghinejad, Sajjad Abdollahramezani, Qitong Li, Eric V. Woods | Summary: Achieving deterministic control over the properties of low-dimensional materials with nanoscale precision is a long-sought goal. Mastering this capability has a transformative impact on the design of multifunctional electrical and optical devices. Here, we […]


Continue.. Ion-Assisted Nanoscale Material Engineering in Atomic Layers

How to evaluate your medical time series classification?

Kavli Affiliate: Xiang Zhang | First 5 Authors: Yihe Wang, Taida Li, Yujun Yan, Wenzhan Song, Xiang Zhang | Summary: Medical time series (MedTS) play a critical role in many healthcare applications, such as vital sign monitoring and the diagnosis of brain and heart diseases. However, the existence of subject-specific features poses unique challenges in […]


Continue.. How to evaluate your medical time series classification?

Repurposing Foundation Model for Generalizable Medical Time Series Classification

Kavli Affiliate: Xiang Zhang | First 5 Authors: Nan Huang, Haishuai Wang, Zihuai He, Marinka Zitnik, Xiang Zhang | Summary: Medical time series (MedTS) classification is critical for a wide range of healthcare applications such as Alzheimer’s Disease diagnosis. However, its real-world deployment is severely challenged by poor generalizability due to inter- and intra-dataset heterogeneity […]


Continue.. Repurposing Foundation Model for Generalizable Medical Time Series Classification

Takin-VC: Zero-shot Voice Conversion via Jointly Hybrid Content and Memory-Augmented Context-Aware Timbre Modeling

Kavli Affiliate: Xiang Zhang | First 5 Authors: Yuguang Yang, Yu Pan, Jixun Yao, Xiang Zhang, Jianhao Ye | Summary: Zero-shot voice conversion (VC) aims to transform the source speaker timbre into an arbitrary unseen one without altering the original speech content.While recent advancements in zero-shot VC methods have shown remarkable progress, there still remains […]


Continue.. Takin-VC: Zero-shot Voice Conversion via Jointly Hybrid Content and Memory-Augmented Context-Aware Timbre Modeling