Xin Wang

xinwang22's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 11 minutes ago

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Paper • 2512.01374 • Published Dec 1, 2025 • 94

upvoted a paper 23 minutes ago

Adversarial Prompt Tuning for Vision-Language Models

Paper • 2311.11261 • Published Nov 19, 2023 • 1

upvoted a paper 36 minutes ago

AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning

Paper • 2408.01978 • Published Aug 4, 2024 • 1

upvoted a paper 43 minutes ago

FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models

Paper • 2509.19870 • Published Sep 24, 2025 • 1

upvoted a paper 44 minutes ago

TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models

Paper • 2411.13136 • Published Nov 20, 2024 • 1

authored 2 papers about 2 months ago

Safety at Scale: A Comprehensive Survey of Large Model Safety

Paper • 2502.05206 • Published Feb 2, 2025 • 3

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law

Paper • 2507.18576 • Published Jul 24, 2025 • 8

upvoted 3 papers about 2 months ago

Safety at Scale: A Comprehensive Survey of Large Model Safety

Paper • 2502.05206 • Published Feb 2, 2025 • 3

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45^{circ} Law

Paper • 2507.18576 • Published Jul 24, 2025 • 8

Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models

Paper • 2508.01741 • Published Aug 3, 2025 • 1

authored a paper about 2 months ago

Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models

Paper • 2508.01741 • Published Aug 3, 2025 • 1

upvoted 2 papers about 2 months ago

Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?

Paper • 2506.14805 • Published Jun 3, 2025 • 3

LeakyCLIP: Extracting Training Data from CLIP

Paper • 2508.00756 • Published Aug 1, 2025 • 2

authored 4 papers about 2 months ago

Imperceptible Jailbreaking against Large Language Models

Paper • 2510.05025 • Published Oct 6, 2025 • 33

Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?

Paper • 2506.14805 • Published Jun 3, 2025 • 3

LeakyCLIP: Extracting Training Data from CLIP

Paper • 2508.00756 • Published Aug 1, 2025 • 2

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs

Paper • 2511.12710 • Published Nov 16, 2025 • 38

upvoted 2 papers about 2 months ago

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs

Paper • 2511.12710 • Published Nov 16, 2025 • 38

UniREditBench: A Unified Reasoning-based Image Editing Benchmark

Paper • 2511.01295 • Published Nov 3, 2025 • 38

upvoted a paper 3 months ago

Imperceptible Jailbreaking against Large Language Models

Paper • 2510.05025 • Published Oct 6, 2025 • 33