Hengyuan Xu

DobyXu's activity

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

authored a paper 1 day ago

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 2 days ago • 16

upvoted 2 papers 1 day ago

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published 3 days ago • 145

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 2 days ago • 16

submitted a paper to Daily Papers 1 day ago

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 2 days ago • 16

liked a model about 2 months ago

stepfun-ai/Step1X-Edit-v1p2

Image-to-Image • Updated 19 days ago • 760 • • 55

upvoted 3 papers about 2 months ago

REASONEDIT: Towards Reasoning-Enhanced Image Editing Models

Paper • 2511.22625 • Published Nov 27, 2025 • 46

iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation

Paper • 2511.20635 • Published Nov 25, 2025 • 32

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

Paper • 2511.12710 • Published Nov 16, 2025 • 38

liked a Space 3 months ago

Running on Zero

Featured

46

WithAnyone Demo

🏃

46

WithAnyone is capable of generating high-quality, controllab

authored 3 papers 3 months ago

Safety at Scale: A Comprehensive Survey of Large Model Safety

Paper • 2502.05206 • Published Feb 2, 2025 • 3

ViStoryBench: Comprehensive Benchmark Suite for Story Visualization

Paper • 2505.24862 • Published May 30, 2025 • 30

WithAnyone: Towards Controllable and ID Consistent Image Generation

Paper • 2510.14975 • Published Oct 16, 2025 • 84

liked a model 3 months ago

WithAnyone/WithAnyone

Text-to-Image • Updated Oct 20, 2025 • 24

upvoted a paper 3 months ago

WithAnyone: Towards Controllable and ID Consistent Image Generation

Paper • 2510.14975 • Published Oct 16, 2025 • 84

upvoted a paper 6 months ago

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

Paper • 2507.08441 • Published Jul 11, 2025 • 61

upvoted a paper 7 months ago

OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation

Paper • 2506.07977 • Published Jun 9, 2025 • 41

upvoted 4 papers 8 months ago

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers

Paper • 2506.03065 • Published Jun 3, 2025 • 27

ViStoryBench: Comprehensive Benchmark Suite for Story Visualization

Paper • 2505.24862 • Published May 30, 2025 • 30

KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models

Paper • 2505.16707 • Published May 22, 2025 • 45

Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets

Paper • 2505.07747 • Published May 12, 2025 • 61