paper-with-me

Papers

BLOCK: An Open-Source Bi-Stage MLLM Character-to-Skin Pipeline for Minecraft

2026-03-04 · Hengquan Guo arxiv

We present \textbf{BLOCK}, an open-source bi-stage character-to-skin pipeline that generates pixel-perfect Minecraft skins from arbitrary character concepts. BLOCK decomposes the problem into (i) a \textbf{3D preview synthesis stage} driven by a large multimodal model (MLLM) with a carefully designed prompt-and-reference template, producing a consistent dual-panel (front/back) oblique-view Minecraft-style preview; and (ii) a \textbf{skin decoding stage} based on a fine-tuned FLUX.2 model that translates the preview into a skin atlas image. We further propose \textbf{EvolveLoRA}, a progressive LoRA curriculum (text-to-image $\rightarrow$ image-to-image $\rightarrow$ preview-to-skin) that initializes each phase from the previous adapter to improve stability and efficiency. BLOCK is released with all prompt templates and fine-tuned weights to support reproducible character-to-skin generation.

📄 PDF Abstract BibTeX arXiv:2603.03964

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SurgWound-Bench: A Benchmark for Surgical Wound Diagnosis

2025-08-21 · Jiahao Xu, Changchang Yin, Odysseas Chatzipanagiotou, Diamantis Tsilimigras 외 arxiv

Surgical site infection (SSI) is one of the most common and costly healthcare-associated infections and and surgical wound care remains a significant clinical challenge in preventing SSIs and improving patient outcomes. …

Visual Question Answering

Enabling Disaggregated Multi-Stage MLLM Inference via GPU-Internal Scheduling and Resource Sharing

2025-12-19 · Lingxiao Zhao, Haoran Zhou, Yuezhi Che, Dazhao Cheng arxiv

Multimodal large language models (MLLMs) extend LLMs with visual understanding through a three-stage pipeline: multimodal preprocessing, vision encoding, and LLM inference. While these stages enhance capability, they int…

On Domain-Specific Post-Training for Multimodal Large Language Models

2024-11-29 · Daixuan Cheng, Shaohan Huang, Ziyu Zhu, Xintong Zhang 외

Recent years have witnessed the rapid development of general multimodal large language models (MLLMs). However, adapting general MLLMs to specific domains, such as scientific fields and industrial applications, remains l…

DiversityDomain Adaptation

OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks

2025-11-02 · Zhihao Peng, Cheng Wang, Shengyuan Liu, Zhiying Liang 외 arxiv

Brain imaging analysis is crucial for diagnosing and treating brain disorders, and multimodal large language models (MLLMs) are increasingly supporting it. However, current brain imaging visual question-answering (VQA) b…

Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task

2025-05-28 · Yanbei Jiang, Yihao Ding, Chao Lei, Jiayang Ao 외

Current Multimodal Large Language Models (MLLMs) excel in general visual reasoning but remain underexplored in Abstract Visual Reasoning (AVR), which demands higher-order reasoning to identify abstract rules beyond simpl…

Visual Reasoning