PyTorchKR Papers

“Code Generation”

총 10,140편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2502.02584공식 코드 · Papers with Code

QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search

Language agents have become a promising solution to complex interactive tasks. One of the key ingredients to the success of language agents is the reward model on the trajectory of the agentic workflow, which provides valuable guidance during training or inference. However, due to the lack of annotations of intermediate interactions, most existing works use an outcome reward model to optimize policies across entire trajectories. This may lead to sub-optimal policies and hinder the overall performance. To address this, we propose QLASS (Q-guided Language Agent Stepwise Search), to automatically generate annotations by estimating Q-values in a stepwise manner for open language agents. By introducing a reasoning tree and performing process reward modeling, QLASS provides effective intermediate guidance for each step. With the stepwise guidance, we propose a Q-guided generation strategy to enable language agents to better adapt to long-term value, resulting in significant performance improvement during model inference on complex interactive agent tasks. Notably, even with almost half the annotated data, QLASS retains strong performance, demonstrating its efficiency in handling limited supervision. We also empirically demonstrate that QLASS can lead to more effective decision making through qualitative analysis. We will release our code and data.

arXiv:2503.22655공식 코드 · Papers with Code

Unicorn: Text-Only Data Synthesis for Vision Language Model Training

Training vision-language models (VLMs) typically requires large-scale, high-quality image-text pairs, but collecting or synthesizing such data is costly. In contrast, text data is abundant and inexpensive, prompting the question: can high-quality multimodal training data be synthesized purely from text? To tackle this, we propose a cross-integrated three-stage multimodal data synthesis framework, which generates two datasets: Unicorn-1.2M and Unicorn-471K-Instruction. In Stage 1: Diverse Caption Data Synthesis, we construct 1.2M semantically diverse high-quality captions by expanding sparse caption seeds using large language models (LLMs). In Stage 2: Instruction-Tuning Data Generation, we further process 471K captions into multi-turn instruction-tuning tasks to support complex reasoning. Finally, in Stage 3: Modality Representation Transfer, these textual captions representations are transformed into visual representations, resulting in diverse synthetic image representations. This three-stage process enables us to construct Unicorn-1.2M for pretraining and Unicorn-471K-Instruction for instruction-tuning, without relying on real images. By eliminating the dependency on real images while maintaining data quality and diversity, our framework offers a cost-effective and scalable solution for VLMs training. Code is available at https://github.com/Yu-xm/Unicorn.git.

arXiv:2505.19284

RankLLM: A Python Package for Reranking with LLMs

The adoption of large language models (LLMs) as rerankers in multi-stage retrieval systems has gained significant traction in academia and industry. These models refine a candidate list of retrieved documents, often through carefully designed prompts, and are typically used in applications built on retrieval-augmented generation (RAG). This paper introduces RankLLM, an open-source Python package for reranking that is modular, highly configurable, and supports both proprietary and open-source LLMs in customized reranking workflows. To improve usability, RankLLM features optional integration with Pyserini for retrieval and provides integrated evaluation for multi-stage pipelines. Additionally, RankLLM includes a module for detailed analysis of input prompts and LLM responses, addressing reliability concerns with LLM APIs and non-deterministic behavior in Mixture-of-Experts (MoE) models. This paper presents the architecture of RankLLM, along with a detailed step-by-step guide and sample code. We reproduce results from RankGPT, LRL, RankVicuna, RankZephyr, and other recent models. RankLLM integrates with common inference frameworks and a wide range of LLMs. This compatibility allows for quick reproduction of reported results, helping to speed up both research and real-world applications. The complete repository is available at rankllm.ai, and the package can be installed via PyPI.

arXiv:2506.05673

Peer-Ranked Precision: Creating a Foundational Dataset for Fine-Tuning Vision Models from DataSeeds' Annotated Imagery

The development of modern Artificial Intelligence (AI) models, particularly diffusion-based models employed in computer vision and image generation tasks, is undergoing a paradigmatic shift in development methodologies. Traditionally dominated by a "Model Centric" approach, in which performance gains were primarily pursued through increasingly complex model architectures and hyperparameter optimization, the field is now recognizing a more nuanced "Data-Centric" approach. This emergent framework foregrounds the quality, structure, and relevance of training data as the principal driver of model performance. To operationalize this paradigm shift, we introduce the DataSeeds.AI sample dataset (the "DSD"), initially comprised of approximately 10,610 high-quality human peer-ranked photography images accompanied by extensive multi-tier annotations. The DSD is a foundational computer vision dataset designed to usher in a new standard for commercial image datasets. Representing a small fraction of DataSeed.AI's 100 million-plus image catalog, the DSD provides a scalable foundation necessary for robust commercial and multimodal AI development. Through this in-depth exploratory analysis, we document the quantitative improvements generated by the DSD on specific models against known benchmarks and make the code and the trained models used in our evaluation publicly available.

arXiv:2506.11309

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a small draft model with a larger target model) and tensor parallelism has each accelerated decoding. However, conventional approaches fail to apply both simultaneously due to imbalanced compute requirements (between draft and target models), KV-cache inconsistencies, and communication overheads under small-batch tensor-parallelism. This paper introduces SwiftSpec, a system that targets ultra-low latency for LLM decoding. SwiftSpec redesigns the speculative decoding pipeline in an asynchronous and disaggregated manner, so that each component can be scaled flexibly and remove draft overhead from the critical path. To realize this design, SwiftSpec proposes parallel tree generation, tree-aware KV cache management, and fused, latency-optimized kernels to overcome the challenges listed above. Across 5 model families and 6 datasets, SwiftSpec achieves an average of 1.75x speedup over state-of-the-art speculative decoding systems and, as a highlight, serves Llama3-70B at 348 tokens/s on 8 Nvidia Hopper GPUs, making it the fastest known system for low-latency LLM serving at this scale.

arXiv:2606.20250v1cs.CV

약한 지도 조직병리 분할을 위한 단일 단계 계층적 보정

Single-Stage Hierarchical Rectification for Weakly Supervised Histopathology Segmentation

계산 병리학의 기존 약한 지도 시맨틱 분할(WSSS) 방법들은 클래스 활성화 맵(CAM) 생성, 오프라인 의사 마스크(pseudo-mask) 정제, 완전 지도 재학습으로 구성된 다단계 패러다임에 의존합니다. 확립된 방식이지만, 이 비결합(decoupled) 접근법은 근본적인 한계를 가집니다. 다단계 프로세스는 높은 계산 학습 비용을 초래할 뿐만 아니라 오류 전파 문제도 겪습니다. 얕은 CNN 레이어의 국부적 텍스처 편향은 거짓 양성 인공물을 생성하는데, 후속 정제 단계에서 이를 수정하지 못하는 경우가 많습니다. 우리는 간단하면서도 매우 효과적인 접근법을 통해 이러한 지속적인 과제를 해결하기 위해 단일 단계 계층적 보정(SSHR) 프레임워크를 제안합니다. 사후에 CAM을 수동적으로 정제하는 대신, 본 방법은 순전파(forward pass) 도중 중간 특징(feature) 표현을 능동적으로 정화합니다. 우리는 얕은 레이어의 국부적 이상치를 필터링하기 위해 깊은 전역 시맨틱 컨텍스트를 활용하는 계층적 특징(feature) 보정 모듈(HFRM)을 도입합니다. 이 메커니즘은 단일 학습 루프(training loop) 내에서 직접 고충실도 활성화 맵을 생성합니다. LUAD-HistoSeg 및 BCSS 데이터셋에 대한 실험 결과, SSHR이 최신(SOTA) 다단계 방법보다 우수한 성능을 보임을 입증했습니다. 또한, SSHR은 학습 시간을 2배에서 5배 단축합니다. 이러한 효율성은 계산 오버헤드를 최소화하고 대규모 조직병리 워크플로우의 임상 전환을 가속화합니다. 코드는 https://github.com/trongduc-nguyen/SSHR 에서 확인할 수 있습니다.

arXiv:2606.27361v1cs.LG

자기회귀 볼츠만 생성기

Autoregressive Boltzmann Generators

열역학적 평형 상태에서 분자 시스템의 효율적인 샘플링은 통계 물리학의 대표적인 난제입니다. 이 난제는 볼츠만 생성기(BG)의 개발을 이끌었으며, BG는 생성 모델과 정확한 우도(likelihood) 및 중요도 샘플링(importance sampling) 보정을 결합하여 비상관 평형 샘플을 빠르게 생성할 수 있게 합니다. 그러나 현대 BG는 주로 정규화 플로우(NF)에 의존하며, 이는 엄격한 가역성 제약으로 인한 제한적인 표현력(이산 시간) 또는 계산 비용이 높은 우도(연속 시간)라는 문제를 겪습니다. 본 논문에서는 플로우 기반 BG 패러다임에서 벗어나 이러한 한계를 극복하는 새로운 자기회귀 모델링 프레임워크인 자기회귀 볼츠만 생성기(ArBG)를 제안합니다. ArBG는 플로우의 위상적 제약을 우회하고 순차적인 추론 시간 개입을 가능하게 하며, 대규모 언어 모델(LLM)에서 효과적인 아키텍처를 활용하여 향상된 확장성을 제공합니다. 우리는 ArBG가 모든 벤치마크에서 플로우 기반 모델 대비 상당한 성능 향상을 가져오며, 특히 10개 잔기로 구성된 Chignolin과 같은 더 큰 펩타이드 시스템에서 두드러진다는 것을 실증적으로 보여줍니다. 또한, ArBG 프레임워크로 학습된 1억 3,200만 매개변수의 전이 가능한 모델인 Robin을 소개하며, 이는 이전 최고 성능 대비 향상되어 8개 잔기 시스템에서 제로샷 에너지 오류인 E-W$_2$를 60% 이상 감소시킵니다. 코드는 다음 링크에서 확인할 수 있습니다: https://github.com/danyalrehman/autobg.

arXiv:2607.01727v1cs.CL

When Does Generating More Help? Disentangling Fixed-Source Synthesis from Source Expansion in Synthetic Data Scaling

Synthetic data can be scaled along two routes: Source Expansion (SE), which enlarges the source by adding seed materials or generators, and Fixed-Source Synthesis (FSS), which holds the source fixed and scales the generation budget. Existing scaling studies typically expand the source as the data grows, conflating SE with FSS and leaving FSS underexplored. We isolate FSS by holding the seed-question pool and teacher model fixed, varying only the per-question response budget under Rejection Sampling (RS). We adapt the rectified scaling law to FSS, deriving it from how repeated sampling covers a fixed source. Empirically, the derived form, fit on low budgets, predicts performance at the held-out highest budget for every evaluated teacher--student pair. At matched total-sample budgets, SE and FSS are comparable at small budgets; at large budgets, adding seed questions outperforms spending the same budget on more responses. Within FSS, however, neither synthesizing additional questions from the existing seeds nor varying the synthesis protocol outperforms plain RS at matched budgets. FSS is thus a bounded scaling axis and a controlled setting for comparing synthesis protocols. We will release our code and data to facilitate further research.

arXiv:2607.16841v2cs.CV

답변 전에 분명히 보기: 현저성 기반 지각 재정렬을 통한 LVLM 환각 완화

Look Clearly Before Answering: Mitigating Hallucinations in LVLMs via Saliency-Driven Perceptual Realignment

대규모 비전-언어 모델(LVLM)은 멀티모달 이해에서 뛰어난 성능을 보여주었다. 그러나 여전히 환각에 취약하여 시각적 증거와 일치하지 않는 응�답을 생성한다. 기존 완화 방법은 대부분 언어 사전 바이어스 또는 교차 모달 불균형을 다루는 반면, 지각과 메모리에 걸친 점진적 시각적 저하는 충분히 탐구되지 않았다. 본 연구에서는 추론 전 과정에서 시각적 인식의 저하를 완화하는 추가 학습 없는 프레임워크인 Saliency-Driven Perceptual Realignment(SDPR)를 제안한다. 구체적으로, 먼저 비의미적 sink 토큰이 탈취한 어텐션을 해제하여 핵심 시각적 증거를 복원하기 위한 현저성 기반 어텐션 재분배를 도입한다. 둘째, KV 캐시의 공간 왜곡을 확인하고, 생성 과정에서 쿼리 관련 시각적 특징을 보존하기 위한 현저성 기반 캐시 정렬을 제안한다. 마지막으로, 지배적인 언어 사전에 의해 유발되는 부정확한 예측에 페널티를 부과하는 사전 제약 대조 디코딩(prior-constrained contrastive decoding)을 도입한다. 제안한 SDPR은 생성 궤적 전반에 걸친 시각적 인식의 전체적 정렬 덕분에 환각에 강건하다. 다양한 LVLM 아키텍처에 걸친 광범위한 실험에서 SDPR은 추가 학습 없이 최소한의 런타임 오버헤드만으로 환각 및 범용 벤치마크 모두에서 최신(state-of-the-art) 방법들을 능가함을 보여준다. 코드는 \href{https://github.com/PengSyuChen/SDPR}{\color{blue}{here}}에서 이용할 수 있다.

arXiv:2012.00451공식 코드 · Papers with Code

Just Ask: Learning to Answer Questions from Millions of Narrated Videos

Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and prevents scalability. In this work, we propose to avoid manual annotation and generate a large-scale training dataset for video question answering making use of automatic cross-modal supervision. We leverage a question generation transformer trained on text data and use it to generate question-answer pairs from transcribed video narrations. Given narrated videos, we then automatically generate the HowToVQA69M dataset with 69M video-question-answer triplets. To handle the open vocabulary of diverse answers in this dataset, we propose a training procedure based on a contrastive loss between a video-question multi-modal transformer and an answer transformer. We introduce the zero-shot VideoQA task and show excellent results, in particular for rare answers. Furthermore, we demonstrate our method to significantly outperform the state of the art on MSRVTT-QA, MSVD-QA, ActivityNet-QA and How2QA. Finally, for a detailed evaluation we introduce iVQA, a new VideoQA dataset with reduced language biases and high-quality redundant manual annotations. Our code, datasets and trained models are available at https://antoyang.github.io/just-ask.html.

arXiv:2108.09713

Robustness-via-Synthesis: Robust Training with Generative Adversarial Perturbations

Upon the discovery of adversarial attacks, robust models have become obligatory for deep learning-based systems. Adversarial training with first-order attacks has been one of the most effective defenses against adversarial perturbations to this day. The majority of the adversarial training approaches focus on iteratively perturbing each pixel with the gradient of the loss function with respect to the input image. However, the adversarial training with gradient-based attacks lacks diversity and does not generalize well to natural images and various attacks. This study presents a robust training algorithm where the adversarial perturbations are automatically synthesized from a random vector using a generator network. The classifier is trained with cross-entropy loss regularized with the optimal transport distance between the representations of the natural and synthesized adversarial samples. Unlike prevailing generative defenses, the proposed one-step attack generation framework synthesizes diverse perturbations without utilizing gradient of the classifier's loss. Experimental results show that the proposed approach attains comparable robustness with various gradient-based and generative robust training techniques on CIFAR10, CIFAR100, and SVHN datasets. In addition, compared to the baselines, the proposed robust training framework generalizes well to the natural samples. Code and trained models will be made publicly available.

arXiv:2109.12302공식 코드 · Papers with Code

Learning Neural Templates for Recommender Dialogue System

Though recent end-to-end neural models have shown promising progress on Conversational Recommender System (CRS), two key challenges still remain. First, the recommended items cannot be always incorporated into the generated replies precisely and appropriately. Second, only the items mentioned in the training corpus have a chance to be recommended in the conversation. To tackle these challenges, we introduce a novel framework called NTRD for recommender dialogue system that decouples the dialogue generation from the item recommendation. NTRD has two key components, i.e., response template generator and item selector. The former adopts an encoder-decoder model to generate a response template with slot locations tied to target items, while the latter fills in slot locations with the proper items using a sufficient attention mechanism. Our approach combines the strengths of both classical slot filling approaches (that are generally controllable) and modern neural NLG approaches (that are generally more natural and accurate). Extensive experiments on the benchmark ReDial show our NTRD significantly outperforms the previous state-of-the-art methods. Besides, our approach has the unique advantage to produce novel items that do not appear in the training set of dialogue corpus. The code is available at \url{https://github.com/jokieleung/NTRD}.

arXiv:2203.04292공식 코드 · Papers with Code

Towards performant and reliable undersampled MR reconstruction via diffusion model sampling

Magnetic Resonance (MR) image reconstruction from under-sampled acquisition promises faster scanning time. To this end, current State-of-The-Art (SoTA) approaches leverage deep neural networks and supervised training to learn a recovery model. While these approaches achieve impressive performances, the learned model can be fragile on unseen degradation, e.g. when given a different acceleration factor. These methods are also generally deterministic and provide a single solution to an ill-posed problem; as such, it can be difficult for practitioners to understand the reliability of the reconstruction. We introduce DiffuseRecon, a novel diffusion model-based MR reconstruction method. DiffuseRecon guides the generation process based on the observed signals and a pre-trained diffusion model, and does not require additional training on specific acceleration factors. DiffuseRecon is stochastic in nature and generates results from a distribution of fully-sampled MR images; as such, it allows us to explicitly visualize different potential reconstruction solutions. Lastly, DiffuseRecon proposes an accelerated, coarse-to-fine Monte-Carlo sampling scheme to approximate the most likely reconstruction candidate. The proposed DiffuseRecon achieves SoTA performances reconstructing from raw acquisition signals in fastMRI and SKM-TEA. Code will be open-sourced at www.github.com/cpeng93/DiffuseRecon.

arXiv:2206.08361

Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields

Capitalizing on the recent advances in image generation models, existing controllable face image synthesis methods are able to generate high-fidelity images with some levels of controllability, e.g., controlling the shapes, expressions, textures, and poses of the generated face images. However, these methods focus on 2D image generative models, which are prone to producing inconsistent face images under large expression and pose changes. In this paper, we propose a new NeRF-based conditional 3D face synthesis framework, which enables 3D controllability over the generated face images by imposing explicit 3D conditions from 3D face priors. At its core is a conditional Generative Occupancy Field (cGOF) that effectively enforces the shape of the generated face to commit to a given 3D Morphable Model (3DMM) mesh. To achieve accurate control over fine-grained 3D face shapes of the synthesized image, we additionally incorporate a 3D landmark loss as well as a volume warping loss into our synthesis algorithm. Experiments validate the effectiveness of the proposed method, which is able to generate high-fidelity face images and shows more precise 3D controllability than state-of-the-art 2D-based controllable face synthesis methods. Find code and demo at https://keqiangsun.github.io/projects/cgof.

arXiv:2211.06719공식 코드 · Papers with Code

Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis

We present a novel bipartite graph reasoning Generative Adversarial Network (BiGraphGAN) for two challenging tasks: person pose and facial image synthesis. The proposed graph generator consists of two novel blocks that aim to model the pose-to-pose and pose-to-image relations, respectively. Specifically, the proposed bipartite graph reasoning (BGR) block aims to reason the long-range cross relations between the source and target pose in a bipartite graph, which mitigates some of the challenges caused by pose deformation. Moreover, we propose a new interaction-and-aggregation (IA) block to effectively update and enhance the feature representation capability of both a person's shape and appearance in an interactive way. To further capture the change in pose of each part more precisely, we propose a novel part-aware bipartite graph reasoning (PBGR) block to decompose the task of reasoning the global structure transformation with a bipartite graph into learning different local transformations for different semantic body/face parts. Experiments on two challenging generation tasks with three public datasets demonstrate the effectiveness of the proposed methods in terms of objective quantitative scores and subjective visual realness. The source code and trained models are available at https://github.com/Ha0Tang/BiGraphGAN.

arXiv:2211.11694공식 코드 · Papers with Code

Exploring Discrete Diffusion Models for Image Captioning

The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name DDCap, to allow more decoding flexibility. Unlike image generation, where the output is continuous and redundant with a fixed length, texts in image captions are categorical and short with varied lengths. Therefore, naively applying the discrete diffusion model to text decoding does not work well, as shown in our experiments. To address the performance gap, we propose several key techniques including best-first inference, concentrated attention mask, text length prediction, and image-free training. On COCO without additional caption pre-training, it achieves a CIDEr score of 117.8, which is +5.0 higher than the auto-regressive baseline with the same architecture in the controlled setting. It also performs +26.8 higher CIDEr score than the auto-regressive baseline (230.3 v.s.203.5) on a caption infilling task. With 4M vision-language pre-training images and the base-sized model, we reach a CIDEr score of 125.1 on COCO, which is competitive to the best well-developed auto-regressive frameworks. The code is available at https://github.com/buxiangzhiren/DDCap.

arXiv:2302.02394공식 코드 · Papers with Code

Eliminating Contextual Prior Bias for Semantic Image Editing via Dual-Cycle Diffusion

The recent success of text-to-image generation diffusion models has also revolutionized semantic image editing, enabling the manipulation of images based on query/target texts. Despite these advancements, a significant challenge lies in the potential introduction of contextual prior bias in pre-trained models during image editing, e.g., making unexpected modifications to inappropriate regions. To address this issue, we present a novel approach called Dual-Cycle Diffusion, which generates an unbiased mask to guide image editing. The proposed model incorporates a Bias Elimination Cycle that consists of both a forward path and an inverted path, each featuring a Structural Consistency Cycle to ensure the preservation of image content during the editing process. The forward path utilizes the pre-trained model to produce the edited image, while the inverted path converts the result back to the source image. The unbiased mask is generated by comparing differences between the processed source image and the edited image to ensure that both conform to the same distribution. Our experiments demonstrate the effectiveness of the proposed method, as it significantly improves the D-CLIP score from 0.272 to 0.283. The code will be available at https://github.com/JohnDreamer/DualCycleDiffsion.

arXiv:2303.14038공식 코드 · Papers with Code

Accelerating Vision-Language Pretraining with Free Language Modeling

The state of the arts in vision-language pretraining (VLP) achieves exemplary performance but suffers from high training costs resulting from slow convergence and long training time, especially on large-scale web datasets. An essential obstacle to training efficiency lies in the entangled prediction rate (percentage of tokens for reconstruction) and corruption rate (percentage of corrupted tokens) in masked language modeling (MLM), that is, a proper corruption rate is achieved at the cost of a large portion of output tokens being excluded from prediction loss. To accelerate the convergence of VLP, we propose a new pretraining task, namely, free language modeling (FLM), that enables a 100% prediction rate with arbitrary corruption rates. FLM successfully frees the prediction rate from the tie-up with the corruption rate while allowing the corruption spans to be customized for each token to be predicted. FLM-trained models are encouraged to learn better and faster given the same GPU time by exploiting bidirectional contexts more flexibly. Extensive experiments show FLM could achieve an impressive 2.5x pretraining time reduction in comparison to the MLM-based methods, while keeping competitive performance on both vision-language understanding and generation tasks. Code will be public at https://github.com/TencentARC/FLM.

arXiv:2303.15433공식 코드 · Papers with Code

Anti-DreamBooth: Protecting users from personalized text-to-image synthesis

Text-to-image diffusion models are nothing but a revolution, allowing anyone, even without design skills, to create realistic images from simple text inputs. With powerful personalization tools like DreamBooth, they can generate images of a specific person just by learning from his/her few reference images. However, when misused, such a powerful and convenient tool can produce fake news or disturbing content targeting any individual victim, posing a severe negative social impact. In this paper, we explore a defense system called Anti-DreamBooth against such malicious use of DreamBooth. The system aims to add subtle noise perturbation to each user's image before publishing in order to disrupt the generation quality of any DreamBooth model trained on these perturbed images. We investigate a wide range of algorithms for perturbation optimization and extensively evaluate them on two facial datasets over various text-to-image model versions. Despite the complicated formulation of DreamBooth and Diffusion-based text-to-image models, our methods effectively defend users from the malicious use of those models. Their effectiveness withstands even adverse conditions, such as model or prompt/term mismatching between training and testing. Our code will be available at https://github.com/VinAIResearch/Anti-DreamBooth.git.

arXiv:2307.11530공식 코드 · Papers with Code

UWAT-GAN: Fundus Fluorescein Angiography Synthesis via Ultra-wide-angle Transformation Multi-scale GAN

Fundus photography is an essential examination for clinical and differential diagnosis of fundus diseases. Recently, Ultra-Wide-angle Fundus (UWF) techniques, UWF Fluorescein Angiography (UWF-FA) and UWF Scanning Laser Ophthalmoscopy (UWF-SLO) have been gradually put into use. However, Fluorescein Angiography (FA) and UWF-FA require injecting sodium fluorescein which may have detrimental influences. To avoid negative impacts, cross-modality medical image generation algorithms have been proposed. Nevertheless, current methods in fundus imaging could not produce high-resolution images and are unable to capture tiny vascular lesion areas. This paper proposes a novel conditional generative adversarial network (UWAT-GAN) to synthesize UWF-FA from UWF-SLO. Using multi-scale generators and a fusion module patch to better extract global and local information, our model can generate high-resolution images. Moreover, an attention transmit module is proposed to help the decoder learn effectively. Besides, a supervised approach is used to train the network using multiple new weighted losses on different scales of data. Experiments on an in-house UWF image dataset demonstrate the superiority of the UWAT-GAN over the state-of-the-art methods. The source code is available at: https://github.com/Tinysqua/UWAT-GAN.