PaperHub

Jindong Gu

~Jindong_Gu1

22
论文总数
11.0
年均投稿
5.5
平均评分
接收情况10/22
会议分布
ICLR
16
NeurIPS
3
COLM
2
ICML
1

发表论文 (22 篇)

202515 篇

4.0
4

Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack

ICLR 2025withdrawn
6.4
4

Image Token Matters: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing

NeurIPS 2025Poster
3.5
4

Learning Visual Prompts for Guiding the Attention of Vision Transformers

ICLR 2025Rejected
8.2
4

Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?

NeurIPS 2025Spotlight
6.1
4

Primitive Vision: Improving Diagram Understanding in MLLMs

ICML 2025Poster
5.0
4

Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs

ICLR 2025withdrawn
4.5
4

VIDEOGUARD: PROTECTING VIDEO CONTENT FROM UNAUTHORIZED EDITING

ICLR 2025Rejected
6.0
4

OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization

ICLR 2025withdrawn
6.3
4

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

ICLR 2025Poster
3.5
4

Cracking the Collective Mind: Adversarial Manipulation in Multi-Agent Systems

ICLR 2025withdrawn
4.3
4

LLM Jailbreak Detection for (Almost) Free!

ICLR 2025withdrawn
4.3
4

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

ICLR 2025withdrawn
6.5
4

True Multimodal In-Context Learning Needs Attention to the Visual Context

COLM 2025Poster
4.4
5

Can Editing LLMs Inject Harm?

ICLR 2025Rejected
4.3
4

Typography Leads Semantic Diversifying: Amplifying Adversarial Transferability across Multimodal Large Language Models

ICLR 2025withdrawn
合作者 (20)