PaperHub

Tianwei Zhang

~Tianwei_Zhang1

31
论文总数
15.5
年均投稿
5.6
平均评分
接收情况19/31
会议分布
ICLR
18
NeurIPS
9
ICML
3
COLM
1

发表论文 (31 篇)

202518 篇

5.8
4

An Engorgio Prompt Makes Large Language Model Babble on

ICLR 2025Poster
6.0
4

Impact-driven Context Filtering For Cross-file Code Completion

COLM 2025Poster
5.6
5

REPOFILTER: Adaptive Retrieval Context Trimming for Repository-Level Code Completion

ICLR 2025Rejected
4.0
4

Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint

ICLR 2025Rejected
5.3
3

A Benchmark for Semantic Sensitive Information in LLMs Outputs

ICLR 2025Poster
4.3
4

PRIME: Protect Your Videos From Malicious Editing

ICLR 2025withdrawn
6.8
5

Transstratal Adversarial Attack: Compromising Multi-Layered Defenses in Text-to-Image Models

NeurIPS 2025Spotlight
6.8
4

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack

NeurIPS 2025Poster
6.6
4

TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models

ICML 2025Poster
6.8
4

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

NeurIPS 2025Poster
3.8
8

SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution

ICLR 2025Rejected
6.3
4

TREANT: Red-teaming Text-to-Image Models with Tree-based Semantic Transformations

ICLR 2025Rejected
6.0
6

VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking

ICLR 2025Poster
5.3
4

Warfare: Breaking the Watermark Protection of AI-Generated Content

ICLR 2025Rejected
7.2
4

BSemiFL: Semi-supervised Federated Learning via a Bayesian Approach

ICML 2025Poster
8.2
4

Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning

NeurIPS 2025Poster
8.2
5

Mask Image Watermarking

NeurIPS 2025Poster
4.9
4

Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems

ICML 2025Poster

202413 篇

4.8
4

Alleviating the Effect of Data Imbalance on Adversarial Training

ICLR 2024withdrawn
4.7
3

FedGSE:Gradient-based Sub-model Extraction for Resource-constrained Federated Learning

ICLR 2024withdrawn
6.7
3

You Only Query Once: An Efficient Label-Only Membership Inference Attack

ICLR 2024Poster
5.5
4

State Chrono Representation for Enhancing Generalization in Reinforcement Learning

NeurIPS 2024Poster
5.3
4

ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users

NeurIPS 2024Poster
3.5
4

Rethinking Adversarial Training with Neural Tangent Kernel

ICLR 2024withdrawn
4.8
4

State Chrono Representation for Enhancing Generalization in Reinforcement Learning

ICLR 2024Rejected
4.0
4

Towards the Vulnerability of Watermarking Artificial Intelligence Generated Content

ICLR 2024withdrawn
5.0
4

COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation

NeurIPS 2024Poster
5.8
4

FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation

ICLR 2024Poster
5.6
5

BadEdit: Backdooring Large Language Models by Model Editing

ICLR 2024Poster
5.8
4

Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation

NeurIPS 2024Poster
4.3
3

Omnipotent Adversarial Training in the Wild

ICLR 2024withdrawn
合作者 (20)