{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/clearsight-visual-signal-enhancement-for","title":"ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models","arxiv_id":"2503.13107","date":"2025-03-17","proceeding":"CVPR 2025 1","authors":["Hao Yin","Guangzong Si","Zilei Wang"],"abstract":"Contrastive decoding strategies are widely used to mitigate object hallucinations in multimodal large language models (MLLMs). By reducing over-reliance on language priors, these strategies ensure that generated content remains closely grounded in visual inputs, producing contextually accurate outputs. Since contrastive decoding requires no additional training or external tools, it offers both computational efficiency and versatility, making it highly attractive. However, these methods present two main limitations: (1) bluntly suppressing language priors can compromise coherence and accuracy of generated content, and (2) processing contrastive inputs adds computational load, significantly slowing inference speed. To address these challenges, we propose Visual Amplification Fusion (VAF), a plug-and-play technique that enhances attention to visual signals within the model's middle layers, where modality fusion predominantly occurs. This approach enables more effective capture of visual features, reducing the model's bias toward language modality. Experimental results demonstrate that VAF significantly reduces hallucinations across various MLLMs without affecting inference speed, while maintaining coherence and accuracy in generated outputs.","url_abs":"https://arxiv.org/abs/2503.13107v1","url_pdf":"https://arxiv.org/pdf/2503.13107v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"clearsight-visual-signal-enhancement-for","repo_url":"https://github.com/ustc-hyin/ClearSight","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"object-hallucination","task_name":"Object Hallucination"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2503.13107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13107"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ustc-hyin/ClearSight","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ustchyin/ClearSight","reach":{"status":"gone","observed_at":"2026-09-16","how":"tree_404+repo_404"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"30a79df235edf108","entry":"AttnAdapter","repo":"ustc-hyin/ClearSight","repo_kind":"official","path":"visaug/inference/AttnAdapter.py","file_url":"https://github.com/ustc-hyin/ClearSight/blob/HEAD/visaug/inference/AttnAdapter.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"30a79df235edf108"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}