Elamur Research⌕
☰
home / papers / 2026 / ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis

ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis

Paper · 2026 · Aashish Anantha Ramakrishnan, Sharon X Huang and Dongwon Lee

Summary

Most text-to-image (T2I) benchmarks use short, literal prompts. Real captions, such as those in journalism, are often abstractive: they mention several interacting subjects, carry background context and use varied syntax. CLIP-based encoders handle these poorly. The authors build ANCHOR, a dataset of more than 70K news image-caption pairs drawn from VisualNews and NYTimes800K. It has two parts. One is a Non-Entity subset with face-free images, which isolates how the caption itself is understood. The other is an Entity subset centered on PERSON entities, grounded through entity linking and face recognition. Experiments on ANCHOR show that current models struggle with multi-subject scenes, context disambiguation and entity resolution.

To address this, the authors propose SAFE (Subject-Aware Fine-tuning). An LLM identifies the key subjects of a caption, and their weight is boosted directly in the text embedding. Fine-tuning combines LoRA with ReFL-style reward objectives. SAFE improves caption consistency and human-preference scores. It needs only one LLM query, adds no encoder parameters and also helps on CC3M, making it a cheap plug-in fix.

Key points

  • Data construction: About 1.8M raw news samples were filtered, discarding roughly 95% as low quality.
    • The Non-Entity subset has 72,692 pairs from 5 news outlets, split 90/5/5. Images with faces were removed using a RetinaFace detector.
    • The Entity subset has 7,516 pairs covering 48 named entities, with 50 pairs per entity used for evaluation.
  • Entity grounding pipeline:
    • The REL Entity Linker maps caption mentions to a 2019-07 Wikipedia dump.
    • FaceNet matches each image to Wikipedia reference photos of the entity.
    • Face-aware cropping centers the image on the target person.
  • Subject weighting: The best scale factor was 1.1², i.e. multiplier level x2.
    • At this setting, SAFE (DFE + GPT-3.5) scored ImageReward 0.0664, versus 0.0249 without GPT-3.5.
    • Larger multipliers made results worse.
  • Generalization to CC3M: SAFE raised ImageReward from 0.2414 (Stable Diffusion 2.1) to 0.2700, with HPS V2 essentially unchanged. Smaller LLMs such as Orca Mini-13B still beat the baselines on 2 of 3 metrics.
  • Release and limitations: The dataset is released under CC BY-NC-SA 4.0. Multilingual captions and multi-encoder T2I models are left for future work.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3,320 worksVision & language · 657 works

Cite

Cite as Aashish Anantha Ramakrishnan, Sharon X Huang and Dongwon Lee. 2026. ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.30

@inproceedings{ramakrishnan2026anchor,
  title = {{ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis}},
  author = {Aashish Anantha Ramakrishnan, Sharon X Huang and Dongwon Lee},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.30},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.30}
}

References

85 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Huggingface sentence-transformers/all-MiniLM-L6-v2. https://huggingface.co/ sentence-transformers/all-MiniLM-L6-v2. Accessed: 2024-4-5. ↗
  2. Reza Abbasi, Ali Nazari, Aminreza Sefid, Mohammadali Banayeeanzade, Mohammad Hossein Rohban, and Mahdieh Soleymani Baghshah. 2025. Analyzing CLIP’s performance limitations in multi-object scenarios: A controlled high-resolution study. find
  3. Malihe Alikhani, Sreyasi Nag Chowdhury, Gerard de Melo, and Matthew Stone. 2019. CITE: A corpus of image-text discourse relations. In Proceedings of the 2019 Conference of the North, pages 570–575, Stroudsburg, PA, USA. Association for Computational Linguistics.
  4. Malihe Alikhani, Piyush Sharma, Shengjie Li, Radu Soricut, and Matthew Stone. 2020. Cross-modal coherence modeling for caption generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6525– 6535, Stroudsburg, PA, USA. Association for Computational… find
  5. Aashish Anantha Ramakrishnan, Aadarsh Anantha Ramakrishnan, and Dongwon Lee. 2025a. CORDIAL: Can multimodal large language models effectively understand coherence relationships? In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages… find
  6. Aashish Anantha Ramakrishnan, Aadarsh Anantha Ramakrishnan, and Dongwon Lee. 2025b. IRONIC: Coherence-aware reasoning chains for multi-modal sarcasm detection. In The First Workshop on Pragmatic Reasoning in Language Models (PragLM). find
  7. Aashish Anantha Ramakrishnan, Aadarsh Anantha Ramakrishnan, and Dongwon Lee. 2025c. RONA: Pragmatically diverse image captioning with coherence relations. In Proceedings of the Fourth Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2025), pages 74–86. Association for Computati… find
  8. Amith Ananthram, Elias Stengel-Eskin, Mohit Bansal, and Kathleen McKeown. 2024. See it from my perspective: How language affects cultural bias in image understanding. In The Thirteenth International Conference on Learning Representations. find
  9. James Betker, Gabriel Goh, Li Jing, and Tim Brooks. Improving image generation with better captions. find
  10. Emanuele Bugliarello and Desmond Elliott. 2021. The role of syntactic planning in compositional image captioning. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 593–607, Stroudsburg, PA, USA. Association for Computat… find
  11. Soravit Changpinyo, Piyush Sharma, Nan Ding, and Radu Soricut. 2021. Conceptual 12M: Pushing web-scale image-text pre-training to recognize long-tail visual concepts. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3558–3568. IEEE. find
  12. Junsong Chen, Y U Jincheng, G E Chongjian, Lewei Yao, Enze Xie, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, and Zhenguo Li. 2023. PixArt-α: Fast training of diffusion transformer for photorealistic text-to-image synthesis. In The Twelfth International Conference on Learning Representations. find
  13. Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Dollar, and C Lawrence Zitnick. 2015. Microsoft COCO captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325.
  14. N Cohn. 2003. Visual Syntactic Structures: Towards a Generative Grammar of Visual Language. find
  15. Herbert P Grice. 1975. Logic and conversation. In Speech acts, pages 41–58. Brill. find
  16. Katherine Crowson, Stella Biderman, Daniel Kornis, Dashiell Stander, Eric Hallahan, Louis Castricato, and Edward Raff. 2022. VQGAN-CLIP: Open domain image generation and editing with natural language guidance. arXiv:2204.08583 [cs]. — [arXiv:2204.08583](https://arxiv.org/abs/2204.08583) find
  17. Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. CLIPScore: A reference-free evaluation metric for image captioning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7514–7528, Online and Punta Cana, Dominican Republic. A…
  18. Damian. compel: A prompting enhancement library for transformers-type text embedding systems. find
  19. Jiankang Deng, Jia Guo, Evangelos Ververas, Irene Kotsia, and Stefanos Zafeiriou. 2020. Retinaface: Single-shot multi-level face localisation in the wild. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5203–5212. IEEE. find
  20. Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs trained by a two time-scale update rule converge to a local nash equilibrium. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc. find
  21. Jiankang Deng, Jia Guo, Niannan Xue, and Stefanos Zafeiriou. 2019. ArcFace: Additive angular margin loss for deep face recognition. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. find
  22. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations.
  23. Ming Ding, Zhuoyi Yang, Wenyi Hong, Wendi Zheng, Chang Zhou, Da Yin, Junyang Lin, Xu Zou, Zhou Shao, Hongxia Yang, and Jie Tang. 2021. CogView: mastering text-to-image generation via transformers. In Proceedings of the 35th International Conference on Neural Information Processing Systems, NIPS ’21,…
  24. Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock,… find
  25. Patrick Esser, Sumith Kulal, A Blattmann, Rahim Entezari, Jonas Muller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, Kyle Lacey, Alex Goodwin, Yannik Marek, and Robin Rombach. 2024. Scaling rectified flow transformers for high-resolut… — [arXiv:2403.03206](https://arxiv.org/abs/2403.03206) find
  26. Weixi Feng, Wanrong Zhu, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Xuehai He, Sugato Basu, Xin Eric Wang, and William Yang Wang. 2023. LayoutGPT: compositional visual planning and generation with large language models. In Proceedings of the 37th International Conference on Neural Information Processin… find
  27. Pan Gao, Ying Hu, and Chenyi Zhuang. 2024. Magnet: We never know how text-to-image diffusion models work, until we learn how vision-language models function. In Advances in Neural Information Processing Systems 37, volume 37, pages 57115–57149, San Diego, California, USA. Neural Information Processi… find
  28. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems, volume 27. Curran Associates, Inc. find
  29. Justin Johnson, Bharath Hariharan, Laurens Van Der Maaten, Li Fei-Fei, C Lawrence Zitnick, and Ross Girshick. 2017. Clevr: A diagnostic dataset for compositional language and elementary visual reasoning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2901–291…
  30. Amita Kamath, Jack Hessel, and Kai-Wei Chang. 2023. What’s “up” with vision-language models? investigating their struggle with spatial reasoning. In The 2023 Conference on Empirical Methods in Natural Language Processing. find
  31. Tuomas Kynkäänniemi, Tero Karras, Miika Aittala, Timo Aila, and Jaakko Lehtinen. 2022. The role of ImageNet classes in fréchet inception distance. find
  32. Daiqing Li, Huan Ling, Seung Wook Kim, Karsten Kreis, Sanja Fidler, and Antonio Torralba. 2022. BigDatasetGAN: Synthesizing ImageNet with pixel-wise annotations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 21330–21340. find
  33. Jian Li, Weiheng Lu, Hao Fei, Meng Luo, Ming Dai, Min Xia, Yizhang Jin, Zhenye Gan, Ding Qi, Chaoyou Fu, Ying Tai, Wankou Yang, Yabiao Wang, and Chengjie Wang. 2024a. A survey on benchmarks of multimodal large language models. find
  34. Yifan Li, Anh Dao, Wentao Bao, Zhen Tan, Tianlong Chen, Huan Liu, and Yu Kong. 2024b. Facial affective behavior analysis with instruction tuning. In Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29 – October 4, 2024, Proceedings, Part XVIII, page 165–186, Berlin, Hei… find
  35. Long Lian, Boyi Li, Adam Yala, and Trevor Darrell. 2024. LLM-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models. Transactions on Machine Learning Research. find
  36. Jiayi Liao, Xu Chen, Qiang Fu, Lun Du, Xiangnan He, Xiang Wang, Shi Han, and Dongmei Zhang. 2024. Text-to-image generation for abstract concepts. In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intell… find
  37. Shanchuan Lin and Xiao Yang. 2023. Diffusion model with perceptual loss. find
  38. Fuxiao Liu, Yinghan Wang, Tianlu Wang, and Vicente Ordonez. 2021. Visual news: Benchmark and challenges in news image captioning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6761–6771, Online and Punta Cana, Dominican Republic. Association for Com… find
  39. Pan Lu, Swaroop Mishra, Tony Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. In The 36th Conference on Neural Information Processing Systems (NeurIPS). find
  40. Subhabrata (subho) Mukherjee, Arindam Mitra, Ganesh Jawahar, Sahaj Agarwal, Hamid Palangi, and Ahmed Awadallah. 2023. Orca: Progressive learning from complex explanation traces of GPT-4. arXiv: Computation and Language.
  41. Son Thanh Nguyen. PyPi package “better_profanity” version 0.7.0. find
  42. Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv:2112.10741 [cs]. find
  43. Mayu Otani, Riku Togashi, Yu Sawai, Ryosuke Ishigami, Yuta Nakashima, Esa Rahtu, Janne Heikkilä, and Shin’ichi Satoh. 2023. Toward verifiable and reproducible human evaluation for text-to-image generation. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 14277–142… find
  44. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. arXiv:2103.00020 [cs].
  45. Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with CLIP latents. arXiv:2204.06125 [cs].
  46. Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research, pages 8821–883…
  47. Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bjorn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. find
  48. Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, and Others. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing…
  49. Christian Schlarmann, Naman D Singh, Francesco Croce, and Matthias Hein. 2024. Robust CLIP: Unsupervised adversarial fine-tuning of vision embeddings for robust large vision-language models. ArXiv, abs/2402.12336. — [arXiv:2402.12336](https://arxiv.org/abs/2402.12336) find
  50. Florian Schroff, Dmitry Kalenichenko, and James Philbin. 2015. FaceNet: A unified embedding for face recognition and clustering. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 815–823. IEEE.
  51. Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, and Others. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in neural information process…
  52. Christoph Schuhmann, Robert Kaczmarczyk, Aran Komatsuzaki, Aarush Katta, Richard Vencu, Romain Beaumont, Jenia Jitsev, Theo Coombes, and Clayton Mullis. 2021. LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs. In NeurIPS Workshop Datacentric AI.
  53. Schuhmann C, Köpf A, Vencu R, Coombes T, and Beaumont R. 2022. Laion coco: 600m synthetic captions from laion2b-en. https://laion.ai/blog/ laion-coco/. ↗
  54. Dustin Schwenk, Apoorv Khandelwal, Christopher Clark, Kenneth Marino, and Roozbeh Mottaghi. 2022. A-OKVQA: A benchmark for visual question answering using world knowledge. In Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VIII, page 14…
  55. Piyush Sharma, Nan Ding, Sebastian Goodman, and Radu Soricut. 2018. Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2556–2565,…
  56. Jianyi Wang, Kelvin C K Chan, and Chen Change Loy. 2023a. Exploring CLIP for assessing the look and feel of images. Proceedings of the AAAI Conference on Artificial Intelligence, 37(2):2555–2563. find
  57. Jiaqi Wang, Zhengliang Liu, Lin Zhao, Zihao Wu, Chong Ma, Sigang Yu, Haixing Dai, Qiushi Yang, Yiheng Liu, Songyao Zhang, Enze Shi, Yi Pan, Tuo Zhang, Dajiang Zhu, Xiang Li, Xi Jiang, Bao Ge, Yixuan Yuan, Dinggang Shen, and 2 others. 2023b. Review of large vision models and visual prompt engineering… find
  58. Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the 32nd International Conference on Machine Learning, pages 2256–2265. PMLR.
  59. Ke Wang, Junting Pan, Weikang Shi, Zimu Lu, Houxing Ren, Aojun Zhou, Mingjie Zhan, and Hongsheng Li. 2024a. Measuring multimodal mathematical reasoning with MATH-vision dataset. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track.
  60. Zeliang Song and Xiaofei Zhou. 2021. Exploring explicit and implicit visual relationships for image captioning. In 2021 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE. find
  61. Qizhou Wang, Yong Lin, Yongqiang Chen, Ludwig Schmidt, Bo Han, and Tong Zhang. 2024b. A sober look at the robustness of CLIPs to spurious features. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  62. Tristan Thrush, Ryan Jiang, Max Bartolo, Amanpreet Singh, Adina Williams, Douwe Kiela, and Candace Ross. 2022. Winoground: Probing vision and language models for visio-linguistic compositionality. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5238– 5248. find
  63. Michael Toker, Hadas Orgad, Mor Ventura, Dana Arad, and Yonatan Belinkov. 2024. Diffusion lens: Interpreting text encoders in text-to-image pipelines. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9713–9728. find
  64. Alasdair Tran, Alexander Mathews, and Lexing Xie. 2020. Transform and tell: Entity-aware news image captioning. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 13032–13042, Seattle, WA, USA. IEEE. find
  65. Johannes M van Hulst, Faegheh Hasibi, Koen Dercksen, Krisztian Balog, and Arjen P de Vries. 2020. REL: An entity linker standing on the shoulders of giants. In Proceedings of the 43rd International ACM SI-GIR Conference on Research and Development in Information Retrieval, SIGIR ’20, pages 2197–2200… find
  66. Ashish Vaswani, Noam M Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Neural Inf Process Syst, 30:5998–6008.
  67. Ramakrishna Vedantam, Samy Bengio, Kevin Murphy, Devi Parikh, and Gal Chechik. 2017. find
  68. Context-aware Yuyang Wang, Anurag Ranjan, Joshua M Susskind, and Miguel Angel Bautista. 2025. INRFlow: Flow matching for INRs in ambient space. In Forty-second International Conference on Machine Learning. find
  69. Zijie J Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, and Duen Horng Chau. 2023c. Diffusiondb: A large-scale prompt gallery dataset for text-to-image generative models. In Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long pa… find
  70. Xiaoshi Wu, Yiming Hao, Keqiang Sun, Yixiong Chen, Feng Zhu, Rui Zhao, and Hongsheng Li. 2023. Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis. find
  71. Guangxuan Xiao, Tianwei Yin, William T Freeman, Frédo Durand, and Song Han. 2025. Fastcomposer: Tuning-free multi-subject image generation with localized attention. International Journal of Computer Vision, 133(3):1175–1194. find
  72. Chunpu Xu, Hanzhuo Tan, Jing Li, and Piji Li. 2022. Understanding social media cross-modality discourse in linguistic space. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2459–2471, Stroudsburg, PA, USA. Association for Computational Linguistics. find
  73. Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. ImageReward: learning and evaluating human preferences for text-to-image generation. In Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS ’23, Red Hook,… find
  74. Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, and Xiaodong He. 2018. AttnGAN: Fine-grained text to image generation with attentional generative adversarial networks. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1316–1324, Salt Lake City,… find
  75. Jiahui Yu, Yuanzhong Xu, Jing Yu Koh, Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, Ben Hutchinson, Wei Han, Zarana Parekh, Xin Li, Han Zhang, Jason Baldridge, and Yonghui Wu. 2022. Scaling autoregressive models for content-rich text-to-image g… find
  76. Minfeng Zhu, Pingbo Pan, Wei Chen, and Yi Yang. 2019. DM-GAN: Dynamic memory generative adversarial networks for text-to-image synthesis. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5795–5803, Long Beach, CA, USA. IEEE. find
  77. Yongshuo Zong, Ondrej Bohdal, and Timothy Hospedales. 2024. VL-ICL bench: The devil in the details of multimodal in-context learning. In The Thirteenth International Conference on Learning Representations. find
  78. Ge Yuan, Xiaodong Cun, Yong Zhang, Maomao Li, Chenyang Qi, Xintao Wang, Ying Shan, and Huicheng Zheng. 2023. Inserting anybody in diffusion models via celeb basis. find
  79. Yuchen Zeng, Wonjun Kang, Yicong Chen, Hyung Il Koo, and Kangwook Lee. 2024. Can MLLMs perform text-to-image in-context learning? In First Conference on Language Modeling. find
  80. Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. 2017. Understanding deep learning requires rethinking generalization. arXiv:1611.03530 [cs]. find
  81. Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 586–595, Salt Lake City, UT. IEEE. find
  82. Yue Zhang, Zhiyang Xu, Ying Shen, Parisa Kordjamshidi, and Lifu Huang. 2025. SPARTUN3D: Situated spatial understanding of 3D world in large language model. In The Thirteenth International Conference on Learning Representations. find
  83. Mingyang Zhou, Grace Luo, Anna Rohrbach, and Zhou Yu. 2022a. Focus! relevant and sufficient context selection for news image captioning. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6078–6088. find
  84. Victor Zhou. Building a better profanity detection library with scikit-learn. https://victorzhou.com/blog/ better-profanity-detection-with-scikit-learn/. Accessed: 2024-9-11. ↗
  85. Yufan Zhou, Ruiyi Zhang, Changyou Chen, Chunyuan Li, Chris Tensmeyer, Tong Yu, Jiuxiang Gu, Jinhui Xu, and Tong Sun. 2022b. Towards language-free training for text-to-image generation. In Proceedings of the IEEE/CVF Conference on Computer Vision find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ramakrishnan-2026-anchor-llm-driven-subject-conditioning/