collaborators

7 papers

cs.CR2025

Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers

Dongyi Liu, Jiangtong Li

Graph Neural Networks(GNNs) are vulnerable to backdoor attacks, where adversaries implant malicious triggers to manipulate model predictions. Existing trigger generators are often…

cs.CV2025

DynaMind: Reconstructing Dynamic Visual Scenes from EEG by Aligning Temporal Dynamics and Multimodal Semantics to Guided Diffusion

Junxiang Liu, Junming Lin, Jiangtong Li +1

Reconstruction dynamic visual scenes from electroencephalography (EEG) signals remains a primary challenge in brain decoding, limited by the low spatial resolution of EEG, a tempor…

cs.CL2025

InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for Debating

Fuyu Wang, Jiangtong Li, Kun Zhu +1

With the rapid advancements in large language models (LLMs), debating tasks, such as argument quality assessment and debate process simulation, have made significant progress. Howe…

cs.CL2025

FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design

Kai Lan, Jiayong Zhu, Jiangtong Li +3

Large Multimodal Models (LMMs) demonstrate significant cross-modal reasoning capabilities. However, financial applications face challenges due to the lack of high-quality multimoda…

cs.CL2025

CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language Model

Jiangtong Li, Yiyun Zhu, Dawei Cheng +2

Multimodal Large Language Models (MLLMs) have rapidly evolved with the growth of Large Language Models (LLMs) and are now applied in various fields. In finance, the integration of…

eess.SP2025

ALFEE: Adaptive Large Foundation Model for EEG Representation

Wei Xiong, Junming Lin, Jiangtong Li +2

While foundation models excel in text, image, and video domains, the critical biological signals, particularly electroencephalography(EEG), remain underexplored. EEG benefits neuro…