18 papers
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation
Zekai Zhang, Jiahao Li, Jie Zhang +18
While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are often underspecified, implicit, or dependent on up-to-date knowl…
Qwen-Image-2.0-RL Technical Report
Yixian Xu, Kaiyuan Gao, Yuxiang Chen +25
We present Qwen-Image-2.0-RL, a post-training pipeline that applies reinforcement learning from human feedback (RLHF) and on-policy distillation (OPD) to improve both the visual qu…
Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
Niantong Li, Guangzheng Hu, Weixu Qiao +35
Text-to-Image generation has evolved from basic image synthesis into a frequently used core capability in professional creative workflows, where simple text-image alignment can no…
LaGO: Latent Action Guidance for Online Reinforcement Learning
Kuan-Yen Liu, Ren-Jyun Huang, Ti-Rong Wu
Large language models (LLMs) have shown strong potential for planning and sequential decision-making, but prior work often relies on using them as direct controllers, which require…
Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation
Jie Zhang, Xiaoyue Chen, Anzhe Chen +36
We introduce Qwen-RobotWorld, a language-conditioned video world model for embodied intelligence. With natural language as a unified action interface, it predicts physically ground…
WallZero: Mastering the Game of WallGo with Strategic Analysis
Hsing-Yu Chen, Jérôme Arjonilla, I-Chen Wu +1
WallGo is a recently introduced strategic board game popularized by the 2025 Netflix series The Devil's Plan. Although played on a small 7 x 7 board, its combination of stone movem…
Tool-IQA: Augmenting Image Quality Assessment with Simple Tools
Guanyi Qin, Junjie Zhang, Chunming He +4
Vision-Language Models (VLMs) have been increasingly adopted for Image Quality Assessment (IQA). However, current methods typically employ a static one-shot scoring paradigm, despi…
Qwen-Image-Flash: Rethinking the Training Recipe for Few-Step Distillation
Tianhe Wu, Kun Yan, Zikai Zhou +23
Few-step distillation has emerged as a critical component in the development of advanced visual generative foundation models, substantially reducing inference overhead while enabli…
Qwen-Image-VAE-2.0 Technical Report
Zekai Zhang, Deqing Li, Kuan Cao +27
We present Qwen-Image-VAE-2.0, a suite of high-compression Variational Autoencoders (VAEs) that achieve significant advances in both reconstruction fidelity and diffusability. To a…
Qwen-Image-2.0 Technical Report
Bing Zhao, Chenfei Wu, Deqing Li +72
We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework. Despite rece…
Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation
Ruibin Li, Tao Yang, Fangzhou Ai +4
Streaming video generation (SVG) distills a pretrained bidirectional video diffusion model into an autoregressive model equipped with sliding window attention (SWA). However, SWA i…
Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models
Qiyuan Zhang, Yufei Wang, Tianhe Wu +5
Recent advancements in Generative Reward Models (GRMs) have demonstrated that scaling the length of Chain-of-Thought (CoT) reasoning considerably enhances the reliability of evalua…
ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking
Kanglong Fan, Tianhe Wu, Wen Wen +6
Reasoning-induced vision-language models (VLMs) advance image quality assessment (IQA) with textual reasoning, yet their scalar scores often lack sensitivity and collapse to a few…
Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
Tianhe Wu, Ruibin Li, Lei Zhang +1
Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing…
DPO-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang +5
Benefiting from pre-trained text-to-image (T2I) diffusion models, real-world image super-resolution (Real-ISR) methods can synthesize rich and realistic details. However, due to th…
The Unanticipated Asymmetry Between Perceptual Optimization and Assessment
Jiabei Zhang, Qi Wang, Siyu Wu +2
Perceptual optimization is primarily driven by the fidelity objective, which enforces both semantic consistency and overall visual realism, while the adversarial objective provides…
VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank
Tianhe Wu, Jian Zou, Jie Liang +2
DeepSeek-R1 has demonstrated remarkable effectiveness in incentivizing reasoning and generalization capabilities of large language models (LLMs) through reinforcement learning. Nev…
Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption
Du Chen, Tianhe Wu, Kede Ma +1
Full-reference image quality assessment (FR-IQA) generally assumes that reference images are of perfect quality. However, this assumption is flawed due to the sensor and optical li…