Picture for Tieniu Tan

Tieniu Tan

Dark Miner: Defend against unsafe generation for text-to-image diffusion models

Add code
Sep 26, 2024
Viaarxiv icon

MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

Add code
Aug 23, 2024
Figure 1 for MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
Figure 2 for MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
Figure 3 for MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
Figure 4 for MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
Viaarxiv icon

Artificial Immune System of Secure Face Recognition Against Adversarial Attacks

Add code
Jun 26, 2024
Viaarxiv icon

Enhancing End-to-End Autonomous Driving with Latent World Model

Add code
Jun 12, 2024
Viaarxiv icon

Artifact Feature Purification for Cross-domain Detection of AI-generated Images

Add code
Mar 17, 2024
Viaarxiv icon

KEBench: A Benchmark on Knowledge Editing for Large Vision-Language Models

Add code
Mar 12, 2024
Viaarxiv icon

Debiasing Large Visual Language Models

Add code
Mar 08, 2024
Figure 1 for Debiasing Large Visual Language Models
Figure 2 for Debiasing Large Visual Language Models
Figure 3 for Debiasing Large Visual Language Models
Figure 4 for Debiasing Large Visual Language Models
Viaarxiv icon

Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models

Add code
Feb 18, 2024
Viaarxiv icon

Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models

Add code
Feb 06, 2024
Viaarxiv icon

A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation

Add code
Feb 06, 2024
Figure 1 for A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Figure 2 for A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Figure 3 for A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Figure 4 for A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Viaarxiv icon