Elamur Research⌕
☰
home / papers / 2025 / Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs

Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs

Paper · 2025 · Xiaofeng Zhang, Yihao Quan, Chen Shen et al.

Summary

The paper investigates why large vision-language models (LVLMs) hallucinate, focusing on attention over image tokens, which make up most of the input. Using LLaVA1.5-7B captioning on 5,000 MSCOCO images, plus checks on Minigpt4, MiniGemini, Qwen-VL and Intern-VL, the authors find a consistent pattern. Attention heads in the first two layers that spread "sink" attention across many image-token columns (dense vision sink heads) are associated with faithful output. Tokens produced when few such heads are active, or when sinks are sparse, are more likely to be hallucinations.

Based on this, they propose EVAS (Enhancing Vision Attention Sink), a training-free, plug-and-play method. In a shallow layer, EVAS selects the head with the densest visual sink and copies its attention map to the other heads in that layer. This pushes the whole layer toward a shared, image-wide focus.

EVAS reduces hallucination on CHAIR and POPE across several LVLMs that use different projectors and decoding strategies. It also improves scores on video benchmarks. The work offers an interpretable, inference-time fix that requires no retraining.

Key points

  • Analysis findings: Dense vision sink heads cluster in layers 1–2. Hallucinated tokens coincide with fewer dense sink heads in these layers. Lower skewness of the sink-density distribution correlates with lower CHAIR_I in captioning and fewer hallucinations in VQA.
  • Best configuration: On LLaVA1.5-7B, the best setting was layer 2, β = 0.002, broadcasting the top-1 head. This cut CHAIR_S from 51.0 to about 36.5 and CHAIR_I from 15.2 to 9.9, while POPE-F1 rose from 84.9 to about 85.7.
  • Generality: EVAS was tested on Shikra, LLaVA, InstructBLIP (beam search, size 5), Intern-VL, Qwen-VL and Mini-Gemini, which use Linear, MLP, cross-attention and Q-former projectors. POPE-F1 gains ranged from roughly +0.6 to +1.4.
  • Video results: On LLaVA-onevision, EgoSchema rose 60.1→63.9, MVBench 56.7→59.9 and VideoMME 58.29→61.16. VideoLLaMA2 gained between +3.5 and +4.48 on the same three benchmarks.
  • Limitations and resources: The authors note that a fundamental fix likely requires better projector alignment and training methods such as RLHF. Code is available at github.com/itsqyh/Shallow-Focus-Deep-Fixes.

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 2The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksComputer Vision and Pattern Recognition · 2,869 works

Cite

Cite as Xiaofeng Zhang, Yihao Quan, Chen Shen, Chaochen Gu, Xiaosong Yuan, Shaotian Yan, Jiawei Cao, Hao Cheng, Kaijie Wu and Jieping Ye. 2025. Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.emnlp-main.174

@inproceedings{zhang2025shallow,
  title = {{Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs}},
  author = {Xiaofeng Zhang, Yihao Quan, Chen Shen, Chaochen Gu, Xiaosong Yuan, Shaotian Yan, Jiawei Cao, Hao Cheng, Kaijie Wu and Jieping Ye},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  doi = {10.18653/v1/2025.emnlp-main.174},
  url = {https://doi.org/10.18653/v1/2025.emnlp-main.174}
}

References

80 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Wenbin An, Feng Tian, Sicong Leng, Jiahao Nie, Haonan Lin, QianYing Wang, Guang Dai, Ping Chen, and Shijian Lu. 2024. Agla: Mitigating object hallucinations in large vision-language models with assembly of global and local attention. arXiv preprint arXiv:2406.12718. — [arXiv:2406.12718](https://arxiv.org/abs/2406.12718) find
  2. Jiaqi Bai, Hongcheng Guo, Zhongyuan Peng, Jian Yang, Zhoujun Li, Mohan Li, and Zhihong Tian. 2025. 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. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966.
  4. 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
  5. 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
  6. 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
  7. 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
  8. Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, and Rui Zhao. 2023. Shikra: Unleashing multimodal llm’s referential dialogue magic. arXiv preprint arXiv:2306.15195.
  9. Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Junyang Lin, Chang Zhou, and Baobao Chang. 2024b. An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models. 18th European Conference on Computer Vision ECCV 2024.
  10. Zhaorun Chen, Zhuokai Zhao, Hongyin Luo, Huaxiu Yao, Bo Li, and Jiawei Zhou. 2024c. Halc: Object hallucination reduction via adaptive focal-contrast decoding. arXiv preprint arXiv:2403.00425. — [arXiv:2403.00425](https://arxiv.org/abs/2403.00425) find
  11. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al. 2024d. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern…
  12. Zesen Cheng, Sicong Leng, Hang Zhang, Yifei Xin, Xin Li, Guanzheng Chen, Yongxin Zhu, Wenqi Zhang, Ziyang Luo, Deli Zhao, et al. 2024. Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms. arXiv preprint arXiv:2406.07476. find
  13. Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James Glass, and Pengcheng He. 2023. Dola: Decoding by contrasting layers improves factuality in large language models. arXiv preprint arXiv:2309.03883.
  14. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168.
  15. Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi. 2024. Instructblip: Towards general-purpose vision-language models with instruction tuning. Advances in Neural Information Processing Systems, 36.
  16. 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
  17. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783.
  18. Chaoyou Fu, Yuhan Dai, Yongdong Luo, Lei Li, Shuhuai Ren, Renrui Zhang, Zihan Wang, Chenyu Zhou, Yunhang Shen, Mengdan Zhang, et al. 2024. Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis. arXiv preprint arXiv:2405.21075.
  19. 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
  20. Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob, et al. 2023. Hallusionbench: An advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. arXiv preprint arXiv:2310…
  21. Danna Gurari, Qing Li, Abigale J Stangl, Anhong Guo, Chi Lin, Kristen Grauman, Jiebo Luo, and Jeffrey P Bigham. 2018. Vizwiz grand challenge: Answering visual questions from blind people. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3608–3617. find
  22. 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.
  23. 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… find
  24. 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
  25. Seil Kang, Jinyeong Kim, Junhyeok Kim, and Seong Jae Hwang. 2025. See what you are told: Visual attention sink in large multimodal models. find
  26. 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
  27. Sicong Leng, Hang Zhang, Guanzheng Chen, Xin Li, Shijian Lu, Chunyan Miao, and Lidong Bing. 2024. Mitigating object hallucinations in large vision-language models through visual contrastive decoding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13872–13…
  28. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, et al. 2024a. Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326.
  29. 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.
  30. Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. 2024b. Inference-time intervention: Eliciting truthful answers from a language model. Advances in Neural Information Processing Systems, 36.
  31. Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, Yi Liu, Zun Wang, Jilan Xu, Guo Chen, Ping Luo, et al. 2024c. Mvbench: A comprehensive multi-modal video understanding benchmark. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22195–22206.
  32. Drew A Hudson and Christopher D Manning. 2019. Gqa: A new dataset for real-world visual reasoning and compositional question answering. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6700–6709.
  33. Shawn Li, Jiashu Qu, Yuxiao Zhou, Yuehan Qin, Tiankai Yang, and Yue Zhao. 2025a. Treble counterfactual vlms: A causal approach to hallucination. arXiv preprint arXiv:2503.06169. find
  34. Fushuo Huo, Wenchao Xu, Zhong Zhang, Haozhao Wang, Zhicheng Chen, and Peilin Zhao. 2025. Self-introspective decoding: Alleviating hallucinations for large vision-language models. In The Thirteenth International Conference on Learning Representations. find
  35. Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, et al. 2025b. Mitigating object hallucinations in mllms via multi-frequency perturbations. arXiv preprint arXiv:2503.14895. find
  36. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. find
  37. Yanwei Li, Yuechen Zhang, Chengyao Wang, Zhisheng Zhong, Yixin Chen, Ruihang Chu, Shaoteng Liu, and Jiaya Jia. 2024d. Mini-gemini: Mining the potential of multi-modality vision language models. arXiv preprint arXiv:2403.18814. find
  38. 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.
  39. 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
  40. Stephanie Lin, Jacob Hilton, and Owain Evans. 2021. Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958.
  41. Feilong Tang, Zile Huang, Chengzhi Liu, Qiang Sun, Harry Yang, and Ser-Nam Lim. 2025. Intervening anchor token: Decoding strategy in alleviating hallucinations for MLLMs. In The Thirteenth International Conference on Learning Representations. find
  42. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024a. Visual instruction tuning. Advances in neural information processing systems, 36.
  43. Shi Liu, Kecheng Zheng, and Wei Chen. 2024b. 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
  44. Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, et al. 2024c. Mmbench: Is your multi-modal model an all-around player? In European conference on computer vision, pages 216–233. Springer.
  45. 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
  46. 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
  47. Karttikeya Mangalam, Raiymbek Akshulakov, and Jitendra Malik. 2023. Egoschema: A diagnostic benchmark for very long-form video language understanding. Advances in Neural Information Processing Systems, 36:46212–46244. find
  48. 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.
  49. Anna Rohrbach, Lisa Anne Hendricks, Kaylee Burns, Trevor Darrell, and Kate Saenko. 2018. Object hallucination in image captioning. arXiv preprint arXiv:1809.02156.
  50. 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
  51. Mingjie Sun, Xinlei Chen, J. Zico Kolter, and Zhuang Liu. 2024. Massive activations in large language models. arXiv preprint arXiv:2402.17762. find
  52. Qwen Team. 2024. Qwen2.5: A party of foundation models. find
  53. 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
  54. 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
  55. Junyang Wang, Yiyang Zhou, Guohai Xu, Pengcheng Shi, Chenlin Zhao, Haiyang Xu, Qinghao Ye, Ming Yan, Ji Zhang, Jihua Zhu, et al. 2023a. 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
  56. Lean Wang, Lei Li, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, and Xu Sun. 2023b. Label words are anchors: An information flow perspective for understanding in-context learning. arXiv preprint arXiv:2305.14160.
  57. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024. Qwen2-vl: Enhancing vision-language model’s perception of the w…
  58. 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
  59. Sangmin Woo, Jaehyuk Jang, Donguk Kim, Yubin Choi, and Changick Kim. 2024. Ritual: Random image transformations as a universal anti-hallucination lever in lvlms. arXiv preprint arXiv:2405.17821. — [arXiv:2405.17821](https://arxiv.org/abs/2405.17821) find
  60. Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2023. Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453. find
  61. 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
  62. Yun Xing, Yiheng Li, Ivan Laptev, and Shijian Lu. 2024a. Mitigating object hallucination via concentric causal attention. arXiv preprint arXiv:2410.15926. hallucinations in large vision language models for detailed caption. arXiv preprint arXiv:2310.01779. — [arXiv:2410.15926](https://arxiv.org/abs/2410.15926) find
  63. 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
  64. Xiaofeng Zhang, Yihao Quan, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang, and Jieping Ye. 2024a. From redundancy to relevance: Information flow in lvlms across reasoning tasks. arXiv preprint arXiv:2406.06579.
  65. Haochen Xue, Feilong Tang, Ming Hu, Yexin Liu, Qidong Huang, Yulong Li, Chengzhi Liu, Zhongxing Xu, Chong Zhang, Chun-Mei Feng, et al. 2025. Mmrc: A large-scale benchmark for understanding multimodal large language model in real-world conversation. arXiv preprint arXiv:2502.11903. find
  66. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, Jin Xu, Jingren Zhou, Jinze Bai, Jinzheng He, Junyang Lin, Kai D… find
  67. Haolin Yang, Feilong Tang, Ming Hu, Qingyu Yin, Yulong Li, Yexin Liu, Zelin Peng, Peng Gao, Junjun He, Zongyuan Ge, et al. 2025a. Scalingnoise: Scaling inference-time search for generating infinite videos. arXiv preprint arXiv:2503.16400. — [arXiv:2503.16400](https://arxiv.org/abs/2503.16400) find
  68. Haolin Yang, Feilong Tang, Linxiao Zhao, Xiang An, Ming Hu, Huifa Li, Xinlin Zhuang, Boqian Wang, Yifan Lu, Xiaofeng Zhang, et al. 2025b. Streamagent: Towards anticipatory agents for streaming video understanding. arXiv preprint arXiv:2508.01875. — [arXiv:2508.01875](https://arxiv.org/abs/2508.01875) find
  69. 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
  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… find
  71. Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, and Lijuan Wang. 2023. Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490.
  72. 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 Xiaofeng Zhang, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang,… — [arXiv:2406.06579](https://arxiv.org/abs/2406.06579) find
  73. Xiaofeng Zhang, Fanshuo Zeng, and Chaochen Gu. 2024c. Simignore: Exploring and enhancing multimodal large model complex reasoning via similarity computation. Neural Networks, page 107059. find
  74. Xiaofeng Zhang, Fanshuo Zeng, Yihao Quan, Zheng Hui, and Jiawei Yao. 2025. Enhancing multimodal large language models complex reason via similarity computation. AAAI. find
  75. Qiyan Zhao, Xiaofeng Zhang, Yiheng Li, Yun Xing, Xiaosong Yuan, Feilong Tang, Sinan Fan, Xuhang Chen, Xu-Yao Zhang, and Da-Han Wang. 2025. Mca-llava: Manhattan causal attention for reducing hallucination in large vision-language models. The 33rd ACM International Conference on Multimedia. find
  76. Guanyu Zhou, Yibo Yan, Xin Zou, Kun Wang, Aiwei Liu, and Xuming Hu. 2025. Mitigating modality prior-induced hallucinations in multimodal large language models via deciphering attention causality. In The Thirteenth International Conference on Learning Representations. find
  77. Yiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang, Zhun Deng, Chelsea Finn, Mohit Bansal, and Huaxiu Yao. 2023. Analyzing and mitigating object hallucination in large vision-language models. arXiv preprint arXiv:2310.00754. find
  78. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592.
  79. Lanyun Zhu, Deyi Ji, Tianrun Chen, Peng Xu, Jieping Ye, and Jun Liu. 2024. Ibd: Alleviating hallucinations in large vision-language models via image-biased decoding. arXiv preprint arXiv:2402.18476. — [arXiv:2402.18476](https://arxiv.org/abs/2402.18476) find
  80. Xinlin Zhuang, Feilong Tang, Haolin Yang, Ming Hu, Huifa Li, Haochen Xue, Yichen Li, Junjun He, Zongyuan Ge, Ying Qian, et al. 2025. Towards efficient medical reasoning with minimal fine-tuning data. arXiv preprint arXiv:2508.01450. — [arXiv:2508.01450](https://arxiv.org/abs/2508.01450) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2025-shallow-focus-deep-fixes-enhancing/