Title: Dongzhi Jiang - Homepage
Open Graph Title: Dongzhi Jiang
Mail addresses
jdzcarr7@gmail.com
jdzcarr7@gmail.com
Opengraph URL: https://github.com/
Domain: caraj7.github.io
| og:locale | en |
| og:site_name | Dongzhi Jiang |
| HandheldFriendly | True |
| MobileOptimized | 320 |
| None | on |
| msapplication-TileColor | #000000 |
| msapplication-TileImage | images/mstile-144x144.png?v=M44lzPylqQ |
| msapplication-config | images/browserconfig.xml?v=M44lzPylqQ |
| theme-color | #ffffff |
Links:
| Homepage | https://caraj7.github.io#about-me |
| About Me | https://caraj7.github.io/#about-me |
| News | https://caraj7.github.io/#-news |
| Publications | https://caraj7.github.io/#-publications |
| Projects | https://caraj7.github.io/#projects |
| Github | https://github.com/CaraJ7 |
| Google Scholar | https://scholar.google.com/citations?user=jIR4PAsAAAAJ |
| https://raw.githubusercontent.com/CaraJ7/CaraJ7.github.io/main/images/wechat.jpeg | |
| https://github.com/CaraJ7 | |
| https://scholar.google.com/citations?user=jIR4PAsAAAAJ | |
| https://raw.githubusercontent.com/CaraJ7/CaraJ7.github.io/main/images/wechat.jpeg | |
| Multimedia Lab | https://mmlab.ie.cuhk.edu.hk/ |
| Hongsheng Li | https://www.ee.cuhk.edu.hk/~hsli/ |
| Xiaogang Wang | https://www.ee.cuhk.edu.hk/~xgwang/ |
| Seed 2.1 | https://seed.bytedance.com/en/seed2_1 |
| CoCo | https://arxiv.org/abs/2603.08652 |
| RealGen | https://arxiv.org/abs/2512.00473 |
| Seed 2.0 | https://seed.bytedance.com/en/blog/seed2-0-%E6%AD%A3%E5%BC%8F%E5%8F%91%E5%B8%83 |
| DraCo | https://arxiv.org/pdf/2512.05112 |
| MME-CoF | https://arxiv.org/abs/2510.26802 |
| AR3D-R1 | https://arxiv.org/abs/2512.10949 |
| 🎩 DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation | https://arxiv.org/pdf/2512.05112 |
| UlmEvalkit | https://github.com/ULMEvalKit/ULMEvalKit |
| T2I-R1 | https://arxiv.org/abs/2505.00703 |
| MINT-CoT | https://arxiv.org/abs/2506.05331 |
| BLINK-Twice | https://arxiv.org/abs/2506.05331 |
| MME-CoT | https://arxiv.org/abs/2502.09621 |
| EasyRef | https://arxiv.org/abs/2412.09618 |
| MMSearch | https://arxiv.org/abs/2409.12959 |
| Seed2.1 Model Card: Agentic Intelligence for Productivity | https://seed.bytedance.com/en/blog/seed2-1-officially-released-advancing-ai-productivity |
| Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity | https://seed.bytedance.com/en/blog/seed2-0-%E6%AD%A3%E5%BC%8F%E5%8F%91%E5%B8%83 |
| MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines | https://arxiv.org/abs/2409.12959 |
| MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency | https://arxiv.org/abs/2502.09621 |
| Seed1.8 Model Card: Towards Generalized Real-World Agency | https://arxiv.org/abs/2603.20633 |
| T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT | https://arxiv.org/abs/2505.00703 |
| DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation | https://arxiv.org/pdf/2512.05112 |
| MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems? | https://arxiv.org/pdf/2403.14624.pdf |
| MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning | https://arxiv.org/abs/2506.05331 |
| BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception | https://arxiv.org/ |
| MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine | https://arxiv.org/abs/2407.08739 |
| Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark | https://arxiv.org/abs/2510.26802 |
| Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation | https://arxiv.org/abs/2508.09987 |
| RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards | https://arxiv.org/abs/2512.00473 |
| Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation | https://arxiv.org/abs/2512.10949 |
| Nano-Consistent-150K | https://picotrex.github.io/Awesome-Nano-Banana-images/ |
| Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation | https://arxiv.org/abs/2602.01756 |
| CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation | https://arxiv.org/abs/2603.08652 |
| MoVA: Adapting Mixture of Vision Experts to Multimodal Context | https://arxiv.org/abs/2404.13046 |
| PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models | https://arxiv.org/abs/2503.10529 |
| CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching | https://arxiv.org/abs/2404.03653 |
| EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM | https://arxiv.org/abs/2412.09618 |
| Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction | https://arxiv.org/pdf/2304.00967.pdf |
| UlmEvalkit: An open-source toolkit for evaluating unified large multi-modal models and generative models | https://github.com/ULMEvalKit/ULMEvalKit |
Viewport: width=device-width, initial-scale=1.0
