paper-with-me

Papers

DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation

2025-12-04 · Dongzhi Jiang, Renrui Zhang, Haodong Li, Zhuofan Zong, Ziyu Guo, Jun He, Claire Guo, Junyan Ye, Rongyao Fang, Weijia Li, Rui Liu, Hongsheng Li arxiv

Recent unified multimodal large language models (MLLMs) have shown impressive capabilities, incorporating chain-of-thought (CoT) reasoning for enhanced text-to-image generation. However, existing approaches remain limited, either treating the model merely as a standalone generator or relying on abstract textual planning. To this end, we propose Draft-as-CoT (DraCo), a novel interleaved reasoning paradigm that fully leverages both textual and visual contents in CoT for better planning and verification. Our method first generates a low-resolution draft image as preview, providing more concrete and structural visual planning and guidance. Then, we employ the model's inherent understanding capability to verify potential semantic misalignments between the draft and input prompt, and performs refinement through selective corrections with super-resolution. In this way, our approach addresses two fundamental challenges: the coarse-grained nature of textual planning and the difficulty in generating rare attribute combinations. To support training, we curate DraCo-240K, aiming to enhance three atomic capabilities spanning general correction, instance manipulation, and layout reorganization. Supported by DraCo-CFG, a specialized classifier-free guidance (CFG) strategy for interleaved reasoning, DraCo achieves a tremendous increase on GenEval (+8%), Imagine-Bench (+0.91), and GenEval++ (+3%), significantly outperforming direct generation and other generation methods empowered by CoT.

📄 PDF Abstract BibTeX arXiv:2512.05112

Code (0)

등록된 구현이 없습니다.

Tasks

Text-to-Image Generation

Similar Papers 제목 키워드 기반

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

2026-03-09 · Haodong Li, Chunmei Qing, Huanyu Zhang, Dongzhi Jiang 외 arxiv

Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning. However, existing CoT-based T2…

Text-to-Image GenerationImage Editing

What ZTF Saw Where Rubin Looked: Anomaly Hunting in DR23

2025-07-08 · Maria V. Pruzhinskaya, Anastasia D. Lavrukhina, Timofey A. Semenikhi, Alina A. Volnova 외

We present results from the SNAD VIII Workshop, during which we conducted the first systematic anomaly search in the ZTF fields also observed by LSSTComCam during Rubin Scientific Pipeline commissioning. Using the PineFo…

Anomaly Detection

DRACO: Weakly Supervised Dense Reconstruction And Canonicalization of Objects

2020-11-25 · Rahul Sajnani, AadilMehdi Sanchawala, Krishna Murthy Jatavallabhula, Srinath Sridhar 외

We present DRACO, a method for Dense Reconstruction And Canonicalization of Object shape from one or more RGB images. Canonical shape reconstruction, estimating 3D object shape in a coordinate space canonicalized for sca…

ObjectPose EstimationTranslation

DRACO: A Denoising-Reconstruction Autoencoder for Cryo-EM

2024-10-15 · Yingjun Shen, Haizhao Dai, Qihe Chen, Yan Zeng 외

Foundation models in computer vision have demonstrated exceptional performance in zero-shot and few-shot tasks by extracting multi-purpose features from large-scale datasets through self-supervised pre-training methods. …

Cryogenic Electron Microscopy (cryo-EM)Denoising

Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion

2024-05-30 · Wei Cheng, Yuhan Wu, Wei Hu

Recent years have witnessed the deployment of code language models (LMs) in various code intelligence tasks such as code completion. Yet, it is challenging for pre-trained LMs to generate correct completions in private r…

Code CompletionRetrievaltext similarity