Image de couverture de livre

Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lin, Honglin, Qin, Chonghan, Liu, Zheng, Pei, Qizhi, Li, Yu, Zhong, Zhanping, Gao, Xin, Wang, Yanfeng, He, Conghui, Wu, Lijun
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
par: Liu, Zheng, et autres
Publié: (2026)

MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
par: Lin, Honglin, et autres
Publié: (2026)

A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis
par: Gao, Xin, et autres
Publié: (2025)

Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training
par: Cao, Chuxue, et autres
Publié: (2026)

MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer
par: Lin, Honglin, et autres
Publié: (2025)

Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
par: Lin, Honglin, et autres
Publié: (2025)

OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value
par: Cai, Mengzhang, et autres
Publié: (2025)

Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs
par: Li, Yu, et autres
Publié: (2026)

CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges
par: Li, Yu, et autres
Publié: (2025)

MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion
par: Pei, Qizhi, et autres
Publié: (2025)

ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning
par: Pei, Qizhi, et autres
Publié: (2025)

Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning
par: Lin, Juekai, et autres
Publié: (2026)

Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights
par: Tian, Juanxi, et autres
Publié: (2025)

Unsafe2Safe: Controllable Image Anonymization for Downstream Utility
par: Dinh, Mih, et autres
Publié: (2026)

Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning
par: Tang, Zinan, et autres
Publié: (2025)

Leveraging BEV Paradigm for Ground-to-Aerial Image Synthesis
par: Ye, Junyan, et autres
Publié: (2024)

LEMMA: Learning from Errors for MatheMatical Advancement in LLMs
par: Pan, Zhuoshi, et autres
Publié: (2025)

CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis
par: Li, Weijia, et autres
Publié: (2024)

Animating the Past: Reconstruct Trilobite via Video Generation
par: Wu, Xiaoran, et autres
Publié: (2024)

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
par: Zheng, Weijie, et autres
Publié: (2024)

Contrastive Learning for Image Complexity Representation
par: Liu, Shipeng, et autres
Publié: (2024)

Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning
par: Li, Yu, et autres
Publié: (2025)

Burst Image Quality Assessment: A New Benchmark and Unified Framework for Multiple Downstream Tasks
par: Liang, Xiaoye, et autres
Publié: (2025)

LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
par: Ye, Junyan, et autres
Publié: (2024)

GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation
par: Yan, Zhiyuan, et autres
Publié: (2025)

MIRAGE: A Multi-modal Benchmark for Spatial Perception, Reasoning, and Intelligence
par: Liu, Chonghan, et autres
Publié: (2025)

Benchmarking PathCLIP for Pathology Image Analysis
par: Zheng, Sunyi, et autres
Publié: (2024)

Downstream Task Inspired Underwater Image Enhancement: A Perception-Aware Study from Dataset Construction to Network Design
par: Lin, Bosen, et autres
Publié: (2026)

Benchmarking Scientific Image Forgery Detectors
par: Cardenuto, João P., et autres
Publié: (2021)

EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation
par: Pei, Baoqi, et autres
Publié: (2024)

Where am I? Cross-View Geo-localization with Natural Language Descriptions
par: Ye, Junyan, et autres
Publié: (2024)

PM4Bench: Benchmarking Large Vision-Language Models with Parallel Multilingual Multi-Modal Multi-task Corpus
par: Gao, Junyuan, et autres
Publié: (2025)

REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once
par: Pan, Zhuoshi, et autres
Publié: (2025)

Multi-Scale Global-Instance Prompt Tuning for Continual Test-time Adaptation in Medical Image Segmentation
par: Li, Lingrui, et autres
Publié: (2026)

SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models
par: Liu, Zheng, et autres
Publié: (2024)

SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing
par: Zhang, Tong, et autres
Publié: (2026)

Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks
par: Ding, Yuhe, et autres
Publié: (2024)

Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
par: Kowalczuk, Antoni, et autres
Publié: (2024)

SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation
par: Ye, Junyan, et autres
Publié: (2024)

Instruction-Driven Fusion of Infrared-Visible Images: Tailoring for Diverse Downstream Tasks
par: Yang, Zengyi, et autres
Publié: (2024)