AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents Paper • 2604.02947 • Published 7 days ago • 18
GEditBench v2: A Human-Aligned Benchmark for General Image Editing Paper • 2603.28547 • Published 10 days ago • 33
PixelSmile: Toward Fine-Grained Facial Expression Editing Paper • 2603.25728 • Published 14 days ago • 117
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models Paper • 2603.25502 • Published 14 days ago • 56
PixelSmile: Toward Fine-Grained Facial Expression Editing Paper • 2603.25728 • Published 14 days ago • 117
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5 Paper • 2601.10527 • Published Jan 15 • 26
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5 Paper • 2601.10527 • Published Jan 15 • 26
WithAnyone: Towards Controllable and ID Consistent Image Generation Paper • 2510.14975 • Published Oct 16, 2025 • 87