{"total":29,"items":[{"citing_arxiv_id":"2606.32039","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GEAR: Guided End-to-End AutoRegression for Image Synthesis","primary_cat":"cs.CV","submitted_at":"2026-06-30T17:59:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GEAR jointly trains VQ tokenizer and AR generator end-to-end via dual hard/soft read-out and representation alignment, achieving up to 10x faster ImageNet gFID convergence than LlamaGen-REPA while generalizing across quantizers and to text-to-image.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31326","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Bridging Video Understanding and Generation in a Unified Framework","primary_cat":"cs.CV","submitted_at":"2026-06-30T08:29:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Vega unifies video understanding and generation via shared vocabulary and hybrid autoregressive-diffusion architecture, reporting strong results on VBench and VideoMME.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28266","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning","primary_cat":"cs.CV","submitted_at":"2026-06-26T16:57:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RSICCLLM introduces a post-training framework with RSICI dataset, difference-aware supervised fine-tuning, and dual-negative preference optimization that claims to outperform much larger models on remote sensing image change captioning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.27376","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards","primary_cat":"cs.CV","submitted_at":"2026-06-25T17:59:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A self-evolving framework with proposer-solver-generator roles, Solver Token Entropy, and multi-scale internal evaluation improves unified LMMs on understanding and generation tasks using only self-derived consistency signals.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.27089","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TMP: Tree-structured Mixed-policy Pruning for Large-scale Image Generation and Editing","primary_cat":"cs.CV","submitted_at":"2026-06-25T14:26:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TMP is a pruning framework that reduces HunyuanImage-3.0 from 80B to 20B parameters (75% reduction) and Z-Image turbo from 6B to 4B with limited quality degradation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26984","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Unison: Benchmarking Unified Multimodal Models via Synergistic Understanding and Generation","primary_cat":"cs.CV","submitted_at":"2026-06-25T12:58:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Unison is a new benchmark with unified and decoupled tracks plus Unison-Judge to measure synergy between understanding and generation in multimodal models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18249","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification","primary_cat":"cs.CV","submitted_at":"2026-06-16T17:59:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UniAR uses a shared context-visual tokenizer with bitwise quantization and parallel prediction in an autoregressive framework to unify visual understanding and generation, claiming SOTA on generation and editing tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.13289","ref_index":209,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","primary_cat":"cs.CV","submitted_at":"2026-06-11T12:46:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12575","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation","primary_cat":"cs.CV","submitted_at":"2026-06-10T18:24:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Z-Image Turbo++ narrows the quality gap to 8-step generation via three distillation techniques tailored for the 2-step regime.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04457","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Imagine Before You Draw: Visual Prompt Engineering for Image Generation","primary_cat":"cs.CV","submitted_at":"2026-06-03T05:01:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"VPE inserts an internal autoregressive visual semantic token generation step to guide image token production in unified models, reporting faster convergence, higher quality, and superior editing preservation (PSNR 26.76 vs 19.92) versus external alternatives.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30248","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GenClaw: Code-Driven Agentic Image Generation","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:13:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GenClaw introduces a three-stage code-driven workflow for agentic image generation that inserts programmatic sketches between linguistic reasoning and pixel synthesis.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.25347","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ERNIE-Image Technical Report","primary_cat":"cs.CV","submitted_at":"2026-05-25T02:04:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The paper presents ERNIE-Image, an open-source 8B DiT text-to-image model claiming leading open-source performance and near-commercial results via specialized data construction and DPO alignment.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23903","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","primary_cat":"cs.CV","submitted_at":"2026-05-22T17:59:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21573","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:59:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Lens is a 3.8B-parameter text-to-image model that reaches competitive or superior performance to >6B-parameter systems using 19.3% of the training compute of Z-Image through a densely captioned 800M dataset, multi-resolution batching, semantic VAE, strong language encoder, RL fine-tuning, and 4-step","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21090","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TextSculptor: Training and Benchmarking Scene Text Editing","primary_cat":"cs.CV","submitted_at":"2026-05-20T12:22:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TextSculptor supplies an automated data synthesis pipeline yielding 3.2M samples plus a four-task benchmark that raises open-source scene text editing performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18172","ref_index":16,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs","primary_cat":"cs.AI","submitted_at":"2026-05-18T10:15:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Generative Visual Grounding creates instance-specific visual proxy images from EEG signals to enhance MLLM understanding of brain activity beyond text-only alignment.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16842","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models","primary_cat":"cs.AI","submitted_at":"2026-05-16T06:59:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Proposes HT-GRPO with sketch-then-paint staged updates, prompt-conditioned importance ratios, and hierarchical credit assignment for dMLLMs, reporting gains on GenEval and DPG plus quality metrics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12500","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","primary_cat":"cs.CV","submitted_at":"2026-05-12T17:59:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"Qwen-Image [139] 20B 0.99 0.92 0.89 0.88 0.76 0.77 0.87 NEO-unify [112] 2B 0.99 0.92 0.89 0.86 0.77 0.76 0.87 Tuna-2 [85] 7B 0.99 0.96 0.80 0.91 0.84 0.76 0.87 InternVL-U [126] 1.7B 0.99 0.94 0.74 0.91 0.77 0.74 0.85 LongCat-Next [125] 68BA3B - - - - - - 0.84 Z-Image [7] 6B 1.00 0.94 0.78 0.93 0.62 0.77 0.84 BLIP3-o [14] 1.4B - - - - - - 0.84 X-Omni [42] 12B 0.98 0.95 0.75 0.91 0.71 0.68 0.83 BAGEL [28] 7B 0.99 0.94 0.81 0.88 0.64 0.63 0.82 Janus-Pro [18] 7B 0.99 0.89 0.59 0.90 0.79 0.66 0.80 OmniGen2 [141] 4B 1.00 0.95 0.64 0.88 0.55 0.76 0.80 UniWorld-V1 [75] 12B 0.99 0.93 0.79 0.89 0.49 0.70 0.80 Show-o2 [146] 7B 1.00 0.87 0.58 0.92 0.52 0.62 0.76 SD3-Medium [34] 2B 0.99 0.94 0.72 0.89 0.33 0.60 0."},{"citing_arxiv_id":"2605.11061","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer","primary_cat":"cs.CV","submitted_at":"2026-05-11T17:59:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A pixel-space Diffusion Transformer with Unified Transformer architecture unifies image generation, editing, and personalization in an end-to-end model that maps all inputs to a shared token space and scales from 8B to over 200B parameters.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":", Yang, J., Tai, Y.: Textcrafter: Accu- rately rendering multiple texts in complex visual scenes. arXiv preprint arXiv:2503.23461 (2025) [12] Esser, P ., Kulal, S., Blattmann, A., Entezari, R., Müller, J., Saini, H., Levi, Y., Lorenz, D., Sauer, A., Boesel, F., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: ICML (2024) [13] Geng, Z., Wang, Y., Ma, Y., Li, C., Rao, Y., Gu, S., Zhong, Z., Lu, Q., Hu, H., Zhang, X., et al.: X-omni: Reinforcement learning makes discrete autoregressive image generative models great again. arXiv preprint arXiv:2507.22058 (2025) [14] Ghosh, D., Hajishirzi, H., Schmidt, L.: Geneval: An object-focused framework for evaluat- ing text-to-image alignment."},{"citing_arxiv_id":"2605.09430","ref_index":7,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","primary_cat":"cs.CV","submitted_at":"2026-05-10T09:07:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FlashAR accelerates autoregressive image generation up to 22.9x by post-training a pre-trained raster-scan model with a complementary vertical head and dynamic fusion for two-way next-token prediction.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"direct averaging acts as a low-pass filter in the probability space, which may lead to blurred textures 5 or artifacts. We therefore fuse the two predictions with a learnable fusion gate, rather than simply averaging them. Specifically, for p >0 and q >0 , we compute a context-dependent gate from the two predecessor states: gp,q =σ MLP [h H p,q−1;h V p−1,q ] \u0001\u0001 ,(7) where[·;·]denotes concatenation andσis the sigmoid function. The fused logit is then given by zp,q =g p,q zH p,q−1 + (1−g p,q)z V p−1,q.(8) Notably, for boundary positions, only the available directional prediction is used: the first row is decoded by horizontal logits, and the first column is decoded by vertical logits. The corner token (0,0)is predicted from the conditioning prefix."},{"citing_arxiv_id":"2605.04128","ref_index":33,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","primary_cat":"cs.GR","submitted_at":"2026-05-05T15:49:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"JoyAI-Image unifies visual understanding and generation via an MLLM-MMDiT architecture with spatial training signals to reach competitive benchmark performance and stronger spatial intelligence.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"963 on LongText-Bench-ZH, outperforming existing methods. Compared to prior models that exhibit performance gaps across languages, our model maintains consistently high accuracy in both English and Chinese, indicating stable long-text rendering capability across different language settings. 17 Table 7Quantitative evaluation results on LongText-Bench [33]. Model LongText-Bench-EN↑LongText-Bench-ZH↑ Janus-Pro [21] 0.019 0.006 BLIP3-o [17] 0.021 0.018 HiDream-I1-Full [10] 0.543 0.024 Kolors 2.0 [72] 0.258 0.329 FLUX.1 [Dev] [6] 0.607 0.005 OmniGen2 [86] 0.561 0.059 BAGEL [28] 0.373 0.310 GPT Image 1 [High] [61] 0.956 0.619 X-Omni [33] 0.900 0.814 Seedream 3.0 [32] 0.896 0.878 Z-Image-Turbo [76] 0.917 0."},{"citing_arxiv_id":"2605.08163","ref_index":78,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MULTITEXTEDIT: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing","primary_cat":"cs.CV","submitted_at":"2026-05-04T16:21:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MULTITEXTEDIT benchmark reveals that all tested text-in-image editing models show pronounced degradation on non-English languages, especially Hebrew and Arabic, mainly in text accuracy and script fidelity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24763","ref_index":14,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation","primary_cat":"cs.CV","submitted_at":"2026-04-27T17:59:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24459","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TextGround4M: A Prompt-Aligned Dataset for Layout-Aware Text Rendering","primary_cat":"cs.CV","submitted_at":"2026-04-27T13:28:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TextGround4M supplies 4M prompt-aligned image pairs with layout annotations, enabling autoregressive T2I models to render prompt-specified text more accurately via added span tokens, a new benchmark, and layout-aware metrics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21921","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Context Unrolling in Omni Models","primary_cat":"cs.CV","submitted_at":"2026-04-23T17:58:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Omni is a multimodal model whose native training on diverse data types enables context unrolling, allowing explicit reasoning across modalities to better approximate shared knowledge and improve downstream performance.","context_count":1,"top_context_role":"dataset","top_context_polarity":"use_dataset","context_text":"mni can naturally perform image generation and editing tasks, depending on the modality combination of input contexts. We thus report the performances on various benchmarks, comparing our proposed method with the expertise models. Table 6 presents the main results on both text-to-image and image editing tasks, including GenEval2 [19], DPG [16], LongText-EN [12], Inhouse evaluation, and GEdit [29]. Although prior approaches usually derive expertise models that focus on different tasks respectively,O mni benefits from the MoE architecture and task unification, achieving comparable performances with only 3B activations. 3.3 Video Generation Beyond image generation,O mni can also synthesize videos with various combinations of multimodal instruc-"},{"citing_arxiv_id":"2604.20796","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model","primary_cat":"cs.CV","submitted_at":"2026-04-22T17:20:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LLaDA2.0-Uni unifies multimodal understanding and generation inside one discrete diffusion large language model with a semantic tokenizer, MoE backbone, and diffusion decoder.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.22699","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","primary_cat":"cs.CV","submitted_at":"2025-11-27T18:52:07+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":1,"top_context_role":"dataset","top_context_polarity":"use_dataset","context_text":"3880 0.3303 0.3813 10 RAG-Diffusion [39] 0.4498 0.7797 0.4388 0.3316 0.2116 0.1910 0.2648 11 TextDiffuser-2 [10] 0.4353 0.6765 0.5322 0.3255 0.1787 0.0809 0.2326 12 AnyText [70] 0.4675 0.7432 0.0513 0.1739 0.1948 0.2249 0.1804 LongText-Bench.To further assess our model's capability in rendering longer texts, we evaluate its performance on LongText-Bench [22], a specialized benchmark focusing on evaluating the performance of rendering longer texts in both English and Chinese. As shown in Table 6, our models demonstrate strong and consistent performance across both language settings. On LongText-Bench-EN, Z-Image achieves a competitive score of 0.935, ranking third among all evaluated models, while on LongText-Bench-ZH, it"},{"citing_arxiv_id":"2510.26583","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Emu3.5: Native Multimodal Models are World Learners","primary_cat":"cs.CV","submitted_at":"2025-10-30T15:11:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Emu3.5 is a native multimodal world model pre-trained on over 10 trillion vision-language tokens with next-token prediction, post-trained via reinforcement learning, and accelerated by Discrete Diffusion Adaptation for efficient interleaved generation and world exploration.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"semantically with given text prompts. To evaluate the model's text rendering capability, we conduct evaluation both on English and Chinese text genera- tion. For English text rendering, we utilize the LeX-Bench [129], CVTG-2K [26] benchmark to test the readability of rendered English text. For Chinese text rendering, we performed an evaluation using LongText-Bench [33]. This benchmark is designed to assess how well models render longer texts in both English and Chinese. 6https://github.com/LAION-AI/aesthetic-predictor 7https://github.com/Breakthrough/PySceneDetect 18 Quantitative Evaluation.(1)TIIF:Table 4 presents a comparative analysis of model performance on TIIF-Bench mini [105], a specialized benchmark developed to systematically assess the capability of T2I models in interpreting"},{"citing_arxiv_id":"2508.02324","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Qwen-Image Technical Report","primary_cat":"cs.CV","submitted_at":"2025-08-04T11:49:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Qwen-Image is a foundation model that reaches state-of-the-art results in image generation and editing by combining a large-scale text-focused data pipeline with curriculum learning and dual semantic-reconstructive encoding for editing consistency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}