[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-plug-in-fix-for-ai-models-that-confuse-dogs-with-animals":10,"sections":34},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},3777,"a-plug-in-fix-for-ai-models-that-confuse-dogs-with-animals","A Plug-in Fix for AI Models That Confuse Dogs With Animals","Researchers at PKU have built a regularizer that teaches large multimodal models to respect taxonomic hierarchies without retraining them from scratch.","Most vision-language AI models can identify a golden retriever but stumble when asked to place it correctly in a hierarchy — dog, then canine, then mammal, then animal.\n\nResearchers at Peking University's ICST-MIPL lab published a method called Hierarchical Representation Regularization, or HiR², that adds taxonomy awareness to large multimodal models as a plug-and-play module rather than a ground-up redesign. The system builds a visual tree by pulling coarse-to-fine features from intermediate layers of an existing language model, guided by text cues. Two loss functions do the enforcement work: one uses hyperbolic geometry to make the model respect parent-child concept relationships, and another pushes similar-but-distinct concepts apart angularly without disrupting the hierarchy. The researchers say it works across different model architectures and fine-tuning setups, and the code is already public.\n\nThe gap this targets is real and underappreciated. When a model conflates a category with its parent class — or ranks a sibling concept as more similar than a parent — downstream tasks like image search, medical imaging, and product classification break in subtle, hard-to-debug ways. A regularizer that slots into existing fine-tuning pipelines is a more practical fix than asking teams to redesign their training objectives.\n\nThe catch is that benchmarks on hierarchical visual recognition are still thin, and a technique that scores well on research datasets does not always survive contact with messy production data — a gap the field has seen before with structured prediction methods that looked strong in the lab.","[\"ai\",\"multimodal\",\"computer-vision\",\"research\"]","2026-07-07T04:00:00.000Z","2026-07-07T08:16:04.475Z","2026-07-07T08:16:07.407Z","published",null,[],"ai",[24,26,27,28],"multimodal","computer-vision","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.02909",0,{"sections":35},[36,40,45,50,55,60,65,70,75,79,84,88,93,98],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":18},"Dev Tools","dev-tools",59,{"name":80,"slug":81,"count":82,"latest_published_at":83},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":85,"slug":86,"count":82,"latest_published_at":87},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]