Elamur Research⌕
☰
home / papers / 2026 / Fixing Semantic Blind Spots in Anchor Tokens of dMLLMs

Fixing Semantic Blind Spots in Anchor Tokens of dMLLMs

Paper · 2026 · Ruixuan Xu, Jiexi Xu, Qiyan Zhao et al.

Summary

Diffusion-based multimodal LLMs (dMLLMs) such as LLaDA-V and LaViDa still describe things that are not in the image. The authors traced attention flow on 1000 MSCOCO samples and found two linked causes. First, the image_newline separator tokens act as semantic anchors that soak up attention, so little is left for real image tokens. Second, RoPE's long-range decay causes these anchors to mostly attend to nearby tile tokens. The earlier thumbnail, which carries the global view, ends up under-attended, a gap the authors call "semantic blind spots."

Their fix, EDAR (Extrinsic Distance-Aware Regularization), needs no training. At inference it appends a fixed, distance-aware matrix to the attention keys. This matrix absorbs surplus attention from the anchors and adds an absolute positional bias, so the anchors cover the whole image more evenly.

On LLaDA-V and both LaViDa variants, EDAR lowers hallucination on CHAIR and POPE and also improves general benchmarks. Earlier position re-indexing methods such as CCA and MCA tend to hurt general benchmark scores, while EDAR does not.

Key points

  • Diagnosis: the image_newline tokens show a strong attention sink. Under AnyRes processing, RoPE decay leaves the thumbnail tokens poorly aggregated by these anchors. The effect was confirmed on both LLaDA-V and LaViDa.
  • Hallucination results on LLaDA-V: CHAIR_S drops from 17.4 to 11.2 and CHAIR_I from 6.8 to 4.3. These are the lowest values among the compared methods (CCA, MCA, DoPE, Farsight).
  • General benchmarks: on LLaDA-V, EDAR raises ai2d from 77.8 to 80.6 and MMStar from 60.1 to 62.2. It beats the baseline on every reported metric, though DoPE scores higher on MMMU and MMB. LaViDa-D and LaViDa-L show similar gains; for example, LaViDa-L's CHAIR_S falls from 17.5 to 13.5.
  • Default hyperparameters: M = N (full sequence length), α = 0.01, β = 10.0. Performance peaks at β = 10 and worsens at both lower and higher values.
  • Limitation: the extra key columns enlarge the softmax, which increases inference latency and memory use.

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

 Institutions

🎓Shanghai Jiao Tong UniversityShanghai · China212 works · 19,544 citations🎓Chinese University of Hong KongHong Kong · China159 works · 16,154 citations🎓University of Hong KongPok Fu Lam · China118 works · 13,496 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksComputer Vision and Pattern Recognition · 3,486 works

Cite

Cite as Ruixuan Xu, Jiexi Xu, Qiyan Zhao and Xiaofeng Zhang. 2026. Fixing Semantic Blind Spots in Anchor Tokens of dMLLMs. 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.966

@inproceedings{xu2026fixing,
  title = {{Fixing Semantic Blind Spots in Anchor Tokens of dMLLMs}},
  author = {Ruixuan Xu, Jiexi Xu, Qiyan Zhao and Xiaofeng Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.966},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.966}
}

References

78 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Kyungho Bae, Jinhyung Kim, Sihaeng Lee, Soonyoung Lee, Gunhee Lee, and Jinwoo Choi. 2025. Mash-vlm: Mitigating action-scene hallucination in video-llms through disentangled spatial-temporal representations. arXiv preprint arXiv:2503.15871. — [arXiv:2503.15871](https://arxiv.org/abs/2503.15871) find
  2. Jiaqi Bai, Hongcheng Guo, Zhongyuan Peng, Jian Yang, Zhoujun Li, Mohan Li, and Zhihong Tian. 2025a. Mitigating hallucinations in large vision-language models by adaptively constraining information flow. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 23442–23450. find
  3. Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, Wenbin Ge, Zhifang Guo, Qidong Huang, Jie Huang, Fei Huang, Binyuan Hui, Shutong Jiang, Zhaohai Li, Mingsheng Li, Mei Li, Kaixin Li, Zicheng Lin, Junyang Lin, Xuejing Liu, Ji… — Qwen3-VL Technical Report
  4. Ivana Balažević, Yuge Shi, Pinelopi Papalampidi, Rahma Chaabouni, Skanda Koppula, and Olivier J Hénaff. 2024. Memory consolidation enables long-context video understanding. arXiv preprint arXiv:2402.05861. — [arXiv:2402.05861](https://arxiv.org/abs/2402.05861) find
  5. Liwei Che, Tony Qingze Liu, Jing Jia, Weiyi Qin, Ruixiang Tang, and Vladimir Pavlovic. 2025. Eazy: Eliminating hallucinations in lvlms by zeroing out hallucinatory image tokens. arXiv preprint arXiv:2503.07772. — [arXiv:2503.07772](https://arxiv.org/abs/2503.07772) find
  6. Beitao Chen, Xinyu Lyu, Lianli Gao, Jingkuan Song, and Heng Tao Shen. 2024a. Alleviating hallucinations in large vision-language models through hallucination-induced optimization. arXiv preprint arXiv:2405.15356. — [arXiv:2405.15356](https://arxiv.org/abs/2405.15356) find
  7. Beitao Chen, Xinyu Lyu, Lianli Gao, Jingkuan Song, and Heng Tao Shen. 2025a. Attention hijackers: Detect and disentangle attention hijacking in lvlms for hallucination mitigation. arXiv preprint arXiv:2503.08216. — [arXiv:2503.08216](https://arxiv.org/abs/2503.08216) find
  8. Cong Chen, Mingyu Liu, Chenchen Jing, Yizhou Zhou, Fengyun Rao, Hao Chen, Bo Zhang, and Chunhua Shen. 2025b. Perturbollava: Reducing multimodal hallucinations with perturbative visual training. arXiv preprint arXiv:2503.06486. — [arXiv:2503.06486](https://arxiv.org/abs/2503.06486) find
  9. Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Jiaqi Wang, Yu Qiao, Dahua Lin, et al. 2024b. Are we on the right way for evaluating large vision-language models? arXiv preprint arXiv:2403.20330.
  10. Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, Lixin Gu, Xuehui Wang, Qingyun Li, Yiming Ren, Zixuan Chen, Jiapeng Luo, Jiahao Wang, Tan Jiang, Bo Wang, Conghui He, Botian Shi, Xingcheng Zhang, Han Lv, Yi Wang, Wenqi Shao, Pei… — Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
  11. DeepSeek-AI, :, Xiao Bi, Deli Chen, Guanting Chen, et al. 2024. Deepseek llm: Scaling open-source language models with longtermism. Preprint, arXiv:2401.02954. find
  12. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
  13. Jinhao Duan, Fei Kong, Hao Cheng, James Diffenderfer, Bhavya Kailkhura, Lichao Sun, Xiaofeng Zhu, Xiaoshuang Shi, and Kaidi Xu. 2025. Truth-print: Mitigating lvlm object hallucination via latent truthful-guided pre-intervention. arXiv preprint arXiv:2503.10602. — [arXiv:2503.10602](https://arxiv.org/abs/2503.10602) find
  14. Shansan Gong, Shivam Agarwal, Yizhe Zhang, Jiacheng Ye, Lin Zheng, Mukai Li, Chenxin An, Peilin Zhao, Wei Bi, Jiawei Han, Hao Peng, and Lingpeng Kong. 2025. Scaling diffusion language models via adaptation from autoregressive models. In The Thirteenth International Conference on Learning Representat… find
  15. Xuan Gong, Tianshi Ming, Xinpeng Wang, and Zhihua Wei. 2024. Damro: Dive into the attention mechanism of lvlm to reduce object hallucination. arXiv preprint arXiv:2410.04514. find
  16. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, et al. 2024. The llama 3 herd of models. Preprint, arXiv:2407.21783.
  17. Jihao Gu, Yingyao Wang, Meng Cao, Pi Bu, Jun Song, Yancheng He, Shilong Li, and Bo Zheng. 2024. Token preference optimization with self-calibrated visual-anchored rewards for hallucination mitigation. arXiv preprint arXiv:2412.14487. find
  18. Jinghan He, Kuan Zhu, Haiyun Guo, Junfeng Fang, Zhenglin Hua, Yuheng Jia, Ming Tang, Tat-Seng Chua, and Jinqiao Wang. 2024. Cracking the code of hallucination in lvlms with vision-aware head divergence. arXiv preprint arXiv:2412.13949.
  19. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. 2023. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. arXiv preprint arXiv:2311.05232.
  20. Qidong Huang, Xiaoyi Dong, Pan Zhang, Bin Wang, Conghui He, Jiaqi Wang, Dahua Lin, Weiming Zhang, and Nenghai Yu. 2024. Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation. In Proceedings of the IEEE/CVF Conference on Computer Vis…
  21. Chaoya Jiang, Haiyang Xu, Mengfan Dong, Jiaxing Chen, Wei Ye, Ming Yan, Qinghao Ye, Ji Zhang, Fei Huang, and Shikun Zhang. 2024. Hallucination augmented contrastive learning for multimodal large language model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pag… find
  22. Zhehan Kan, Ce Zhang, Zihan Liao, Yapeng Tian, Wenming Yang, Junyuan Xiao, Xu Li, Dongmei Jiang, Yaowei Wang, and Qingmin Liao. 2024. Catch: Complementary adaptive token-level contrastive decoding to mitigate hallucinations in lvlms. arXiv preprint arXiv:2411.12713. — [arXiv:2411.12713](https://arxiv.org/abs/2411.12713) find
  23. Aniruddha Kembhavi, Mike Salvato, Eric Kolve, Minjoon Seo, Hannaneh Hajishirzi, and Ali Farhadi. 2016. A diagram is worth a dozen images. Preprint, arXiv:1603.07396.
  24. Junho Kim, Hyunjun Kim, Yeonju Kim, and Yong Man Ro. 2024. Code: Contrasting self-generated description to combat hallucination in large multi-modal models. arXiv preprint arXiv:2406.01920. — [arXiv:2406.01920](https://arxiv.org/abs/2406.01920) find
  25. Harrison Lee, Samrat Phatale, Hassan Mansoor, Thomas Mesnard, Johan Ferret, Kellie Lu, Colton Bishop, Ethan Hall, Victor Carbune, Abhinav Rastogi, and Sushant Prakash. 2024. Rlaif vs. rlhf: Scaling reinforcement learning from human feedback with ai feedback. Preprint, arXiv:2309.00267. find
  26. Bin Li, Dehong Gao, Yeyuan Wang, Linbo Jin, Shanqing Yu, Xiaoyan Cai, and Libin Yang. 2025a. Instruction-aligned visual attention for mitigating hallucinations in large vision-language models. arXiv preprint arXiv:2503.18556. — [arXiv:2503.18556](https://arxiv.org/abs/2503.18556) find
  27. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, and Chunyuan Li. 2024. Llava-onevision: Easy visual task transfer. Preprint, arXiv:2408.03326.
  28. Bohao Li, Rui Wang, Guangzhi Wang, Yuying Ge, Yixiao Ge, and Ying Shan. 2023a. Seed-bench: Benchmarking multimodal llms with generative comprehension. arXiv preprint arXiv:2307.16125.
  29. Shawn Li, Jiashu Qu, Yuxiao Zhou, Yuehan Qin, Tiankai Yang, and Yue Zhao. 2025b. Treble counterfactual vlms: A causal approach to hallucination. arXiv preprint arXiv:2503.06169. find
  30. Shufan Li, Konstantinos Kallidromitis, Hritik Bansal, Akash Gokul, Yusuke Kato, Kazuki Kozuka, Jason Kuen, Zhe Lin, Kai-Wei Chang, and Aditya Grover. 2025c. Lavida: A large diffusion model for vision-language understanding. In The Thirty-ninth Annual Conference on Neural Information Processing Syste… find
  31. Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, et al. 2025d. Mitigating object hallucinations in mllms via multi-frequency perturbations. arXiv preprint arXiv:2503.14895. find
  32. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023b. Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355.
  33. Tsung-Yi Lin, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, and Piotr Dollár. 2015. Microsoft coco: Common objects in context. Preprint, arXiv:1405.0312.
  34. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023. Improved baselines with visual instruction tuning. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 26286–26296.
  35. Shi Liu, Weijie Su, Xizhou Zhu, Wenhai Wang, and Jifeng Dai. 2025a. Comemo: Lvlms need image context with image memory. arXiv preprint arXiv:2506.06279. — [arXiv:2506.06279](https://arxiv.org/abs/2506.06279) find
  36. Shi Liu, Kecheng Zheng, and Wei Chen. 2024. Paying more attention to image: A training-free method for alleviating hallucination in lvlms. arXiv preprint arXiv:2407.21771. — [arXiv:2407.21771](https://arxiv.org/abs/2407.21771) find
  37. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. Train…
  38. Ofir Press, Noah A. Smith, and Mike Lewis. 2022. Train short, test long: Attention with linear biases enables input length extrapolation. Preprint, arXiv:2108.12409. find
  39. Anna Rohrbach, Lisa Anne Hendricks, Kaylee Burns, Trevor Darrell, and Kate Saenko. 2018. Object hallucination in image captioning. arXiv preprint arXiv:1809.02156.
  40. Pritam Sarkar, Sayna Ebrahimi, Ali Etemad, Ahmad Beirami, Sercan Ö Arık, and Tomas Pfister. 2024. Mitigating object hallucination via data augmented contrastive tuning. arXiv preprint arXiv:2405.18654. — [arXiv:2405.18654](https://arxiv.org/abs/2405.18654) find
  41. Wei Suo, Lijun Zhang, Mengyang Sun, Lin Yuanbo Wu, Peng Wang, and Yanning Zhang. 2025. Octopus: Alleviating hallucination via dynamic contrastive decoding. arXiv preprint arXiv:2503.00361. — [arXiv:2503.00361](https://arxiv.org/abs/2503.00361) find
  42. Zikang Liu, Longteng Guo, Yepeng Tang, Tongtian Yue, Junxian Cai, Kai Ma, Qingbin Liu, Xi Chen, and Jing Liu. 2025b. Vrope: Rotary position embedding for video large language models. arXiv preprint arXiv:2502.11664. find
  43. Feilong Tang, Zile Huang, Chengzhi Liu, Qiang Sun, Harry Yang, and Ser-Nam Lim. 2025a. Intervening anchor token: Decoding strategy in alleviating hallucinations for MLLMs. In The Thirteenth International Conference on Learning Representations. find
  44. 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. Preprint, arXiv:2209.09513. find
  45. Feilong Tang, Chengzhi Liu, Zhongxing Xu, Ming Hu, Zile Huang, Haochen Xue, Ziyang Chen, Zelin Peng, Zhiwei Yang, Sijin Zhou, et al. 2025b. Seeing far and clearly: Mitigating hallucinations in mllms with attention causal decoding. In Proceedings of the Computer Vision and Pattern Recognition Confere… find
  46. Maria Lymperaiou, Giorgos FIlandrianos, Angeliki Dimitriou, Athanasios Voulodimos, and Giorgos Stamou. 2025. Halcece: A framework for explainable hallucination detection through conceptual counterfactuals in image captioning. arXiv preprint arXiv:2503.00436. — [arXiv:2503.00436](https://arxiv.org/abs/2503.00436) find
  47. Fan Ma, Xiaojie Jin, Heng Wang, Yuchen Xian, Jiashi Feng, and Yi Yang. 2024. Vista-llama: Reducing hallucination in video language models via equal distance to visual tokens. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13151–13160. find
  48. Qwen Team. 2024. Qwen2.5: A party of foundation models. find
  49. Chongjun Tu, Peng Ye, Dongzhan Zhou, Lei Bai, Gang Yu, Tao Chen, and Wanli Ouyang. 2025. Attention reallocation: Towards zero-cost and controllable hallucination mitigation of mllms. arXiv preprint arXiv:2503.08342. — [arXiv:2503.08342](https://arxiv.org/abs/2503.08342) find
  50. Chao Wang, Weiwei Fu, and Yang Zhou. 2025. Tpc: Cross-temporal prediction connection for vision-language model hallucination reduction. arXiv preprint arXiv:2503.04457. — [arXiv:2503.04457](https://arxiv.org/abs/2503.04457) find
  51. Shunqi Mao, Chaoyi Zhang, and Weidong Cai. 2025. Through the magnifying glass: Adaptive perception magnification for hallucination-free vlm decoding. arXiv preprint arXiv:2503.10183.
  52. Jiaqi Wang, Yifei Gao, and Jitao Sang. 2024a. Valid: Mitigating the hallucination of large vision language models by visual layer fusion contrastive decoding. arXiv preprint arXiv:2411.15839. — [arXiv:2411.15839](https://arxiv.org/abs/2411.15839) find
  53. Shen Nie, Fengqi Zhu, Zebin You, Xiaolu Zhang, Jingyang Ou, Jun Hu, JUN ZHOU, Yankai Lin, Ji-Rong Wen, and Chongxuan Li. 2025. Large language diffusion models. In The Thirty-ninth Annual Conference on Neural Information Processing Systems.
  54. Junyang Wang, Yiyang Zhou, Guohai Xu, Pengcheng Shi, Chenlin Zhao, Haiyang Xu, Qinghao Ye, Ming Yan, Ji Zhang, Jihua Zhu, et al. 2023. Evaluation and analysis of hallucination in large vision-language models. arXiv preprint arXiv:2308.15126. — [arXiv:2308.15126](https://arxiv.org/abs/2308.15126) find
  55. Zehao Wang, Xinpeng Liu, Xiaoqian Wu, Yudonglin Zhang, Zhou Fang, Yifan Fang, Junfu Pu, Cewu Lu, and Yong-Lu Li. 2024b. Verb mirage: Unveiling and assessing verb concept hallucinations in multimodal large language models. arXiv preprint arXiv:2412.04939. — [arXiv:2412.04939](https://arxiv.org/abs/2412.04939) find
  56. Koon-Ting Yip, Qiyan Zhao, Wenhao Yu, Xiaofeng Zhang, Jianming Ji, Yanyong Zhang, and Ka-Veng Yuen. 2026b. Cˆ2rope: Causal continuous rotary positional encoding for 3d large multimodal-models reasoning. In 2026 IEEE International Conference on Robotics and Automation (ICRA’ 26). find
  57. Jinfeng Wei and Xiaofeng Zhang. 2024. Dopra: Decoding over-accumulation penalization and re-allocation in specific weighting layer. Proceedings of the 32nd ACM International Conference on Multimedia. find
  58. Zebin You, Shen Nie, Xiaolu Zhang, Jun Hu, Jun Zhou, Zhiwu Lu, Ji-Rong Wen, and Chongxuan Li. 2025. Llada-v: Large language diffusion models with visual instruction tuning. arXiv preprint arXiv:2505.16933.
  59. Wenyi Xiao, Ziwei Huang, Leilei Gan, Wanggui He, Haoyuan Li, Zhelun Yu, Hao Jiang, Fei Wu, and Linchao Zhu. 2024. Detecting and mitigating hallucination in large vision language models via fine-grained ai feedback. arXiv preprint arXiv:2404.14233. — [arXiv:2404.14233](https://arxiv.org/abs/2404.14233) find
  60. Runpeng Yu, Xinyin Ma, and Xinchao Wang. 2025. Dimple: Discrete diffusion multimodal large language model with parallel decoding. Preprint, arXiv:2505.16990. — [arXiv:2505.16990](https://arxiv.org/abs/2505.16990) find
  61. Chunzhao Xie, Tongxuan Liu, Lei Jiang, Yuting Zeng, Yunheng Shen, Weizhe Huang, Jing Li, Xiaohua Xu, et al. 2025a. Tarac: Mitigating hallucination in lvlms via temporal attention real-time accumulative connection. arXiv preprint arXiv:2504.04099. — [arXiv:2504.04099](https://arxiv.org/abs/2504.04099) find
  62. Mingrui Xie, Tianxiang Xu, Qianhai Tang, Shanming Yao, Xiaofeng Zhang, and Junliang Du. 2025b. Dape-br: Distance-aware positional encoding for mitigating object hallucination in lvlms. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 8638–8649. find
  63. Yun Xing, Yiheng Li, Ivan Laptev, and Shijian Lu. 2024a. Mitigating object hallucination via concentric causal attention. arXiv preprint arXiv:2410.15926. — [arXiv:2410.15926](https://arxiv.org/abs/2410.15926) find
  64. Yun Xing, Yiheng Li, Ivan Laptev, and Shijian Lu. 2024b. Mitigating object hallucination via concentric causal attention. arXiv preprint arXiv:2410.15926. — [arXiv:2410.15926](https://arxiv.org/abs/2410.15926) find
  65. Le Yang, Ziwei Zheng, Boxu Chen, Zhengyu Zhao, Chenhao Lin, and Chao Shen. 2024. Nullu: Mitigating object hallucinations in large vision-language models via halluspace projection. arXiv preprint arXiv:2412.13817. — [arXiv:2412.13817](https://arxiv.org/abs/2412.13817) find
  66. Ling Yang, Ye Tian, Bowen Li, Xinchen Zhang, Ke Shen, Yunhai Tong, and Mengdi Wang. 2025. MMaDA: Multimodal large diffusion language models. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. find
  67. Jiacheng Ye, Zhihui Xie, Lin Zheng, Jiahui Gao, Zirui Wu, Xin Jiang, Zhenguo Li, and Lingpeng Kong. 2025. Dream 7b. find
  68. Hao Yin, Guangzong Si, and Zilei Wang. 2025. Clearsight: Visual signal enhancement for object hallucination mitigation in multimodal large language models. arXiv preprint arXiv:2503.13107. — [arXiv:2503.13107](https://arxiv.org/abs/2503.13107) find
  69. Koon-Ting Yip, Qiyan Zhao, Wenhao Yu, Liangyu Yuan, Mingkai Li, Xiaofeng Zhang, Jianmin Ji, Yanyong Zhang, Qing Jiang, and Ka-Veng Yuen. 2026a. Sope: Spherical coordinate-based positional embedding for enhancing spatial perception of 3d lvlms. In Proceedings of the Computer Vision and Pattern Recogn… find
  70. Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, et al. 2024. Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback. In Proceedings of the IEEE/CVF Conference on Computer Vision and…
  71. Liu Yuan, Duan Haodong, Zhang Yuanhan, Li Bo, Zhang Songyang, and Zhao Wangbo. 2023. Mmbench:is your multi-modal model an all-around player. arXiv:2307.06281.
  72. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen. 2024. Mmmu: A massive multi-disc…
  73. Bohan Zhai, Shijia Yang, Xiangchen Zhao, Chenfeng Xu, Sheng Shen, Dongdi Zhao, Kurt Keutzer, Manling Li, Tan Yan, and Xiangjun Fan. 2023. Halle-switch: Rethinking and controlling object existence hallucinations in large vision language models for detailed caption. arXiv preprint arXiv:2310.01779. — [arXiv:2310.01779](https://arxiv.org/abs/2310.01779) find
  74. Xiaofeng Zhang, Yihao Quan, Chaochen Gu, Chen Shen, Xiaosong Yuan, Shaotian Yan, Hao Cheng, Kaijie Wu, and Jieping Ye. 2025. Shallow focus, deep fixes: Enhancing shallow layers vision attention sinks to alleviate hallucination in lvlms. pages 3512–3534.
  75. Xiaofeng Zhang, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang, and Jieping Ye. 2024. From redundancy to relevance: Enhancing explainability in multimodal large language models. arXiv preprint arXiv:2406.06579. — [arXiv:2406.06579](https://arxiv.org/abs/2406.06579) find
  76. Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu, Jiawei Cao, Hao Cheng, and Kaijie Wu. 2026a. What drives attention sinks? a study of massive activations and rotational positional encoding in large vision–language models. Information Processing & Management, 63(2):104431. find
  77. Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu, Xiaosong Yuan, Qiyan Zhao, Jiawei Cao, Feilong Tang, Sinan Fan, Yaomin Shen, Chen Shen, et al. 2026b. Hallucination begins where saliency drops. In The Fourteenth International Conference on Learning Representations. find
  78. Haozhe Zhao, Shuzheng Si, Liang Chen, Yichi Zhang, Maosong Sun, Mingjia Zhang, and Baobao Chang. 2024. Looking beyond text: Reducing language bias in large vision-language models via multimodal dual-attention and soft-image guidance. arXiv preprint arXiv:2411.14279. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/xu-2026-fixing-semantic-blind-spots-anchor/