Jinhe Bi

According to our database, Jinhe Bi authored at least 11 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media.

Rui Lu, Jinhe Bi, Yunpu Ma, Feng Xiao, Yuntao Du, Yijun Tian

CoRR, August, 2025

ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM.

Yujun Wang, Jinhe Bi, Yunpu Ma, Sören Pirk

CoRR, June, 2025

Does Machine Unlearning Truly Remove Model Knowledge? A Framework for Auditing Unlearning in LLMs.

Haokun Chen, Yueqi Zhang, Yuan Bi, Yao Zhang, Tong Liu, Jinhe Bi, Jian Lan, Jindong Gu, Claudia Grosser, Denis Krompass, Nassir Navab, Volker Tresp

CoRR, May, 2025

Backdoor Cleaning without External Guidance in MLLM Fine-tuning.

Xuankun Rong, Wenke Huang, Jian Liang, Jinhe Bi, Xun Xiao, Yiming Li, Bo Du, Mang Ye

CoRR, May, 2025

CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process.

Jinhe Bi, Danqi Yan, Yifan Wang, Wenke Huang, Haokun Chen, Guancheng Wan, Mang Ye, Xun Xiao, Hinrich Schütze, Volker Tresp, Yunpu Ma

CoRR, May, 2025

PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection.

Jinhe Bi, Yifan Wang, Danqi Yan, Xun Xiao, Artur Hecker, Volker Tresp, Yunpu Ma

CoRR, February, 2025

FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models.

Haokun Chen, Hang Li, Yao Zhang, Jinhe Bi, Gengyuan Zhang, Yueqi Zhang, Philip Torr, Jindong Gu, Denis Krompass, Volker Tresp

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering.

Jinhe Bi, Yujun Wang, Haokun Chen, Xun Xiao, Artur Hecker, Volker Tresp, Yunpu Ma

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024

Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering.

Jinhe Bi, Yujun Wang, Haokun Chen, Xun Xiao, Artur Hecker, Volker Tresp, Yunpu Ma

CoRR, 2024

FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models.

Haokun Chen, Hang Li, Yao Zhang, Gengyuan Zhang, Jinhe Bi, Philip Torr, Jindong Gu, Denis Krompass, Volker Tresp

CoRR, 2024

2023

SPOT! Revisiting Video-Language Models for Event Understanding.

Gengyuan Zhang, Jinhe Bi, Jindong Gu, Volker Tresp

CoRR, 2023