VLM | Yixin Zhu | PKUhttps://yzhu.io/tag/vlm/VLMHugo Blox Builder (https://hugoblox.com)en-usSat, 29 Aug 2026 00:00:00 +0000https://yzhu.io/media/icon_hu_d81a9f8bb44f3da0.pngVLMhttps://yzhu.io/tag/vlm/4DStreamCtrl: Interactive Video Generation with Online 4D Controlhttps://yzhu.io/preprint/physics2026/Sat, 29 Aug 2026 00:00:00 +0000https://yzhu.io/preprint/physics2026/[TPAMI26] AffordX: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulationhttps://yzhu.io/publication/hoi2026pami/Sat, 01 Aug 2026 00:00:00 +0000https://yzhu.io/publication/hoi2026pami/Visual Distraction Undermines Moral Reasoning in Vision-Language Modelshttps://yzhu.io/preprint/moral2026mds/Wed, 18 Mar 2026 00:00:00 +0000https://yzhu.io/preprint/moral2026mds/UniAct: Unified Motion Generation and Action Streaming for Humanoid Robotshttps://yzhu.io/preprint/humanoid2026uniact/Thu, 01 Jan 2026 00:00:00 +0000https://yzhu.io/preprint/humanoid2026uniact/[NatureHumanBehaviour26] Combined evidence from artificial neural networks and human brain-lesion models reveals that language modulates vision in human perceptionhttps://yzhu.io/publication/language2025nhb/Sun, 14 Dec 2025 00:00:00 +0000https://yzhu.io/publication/language2025nhb/<script type="text/javascript" src="https://embed.altmetric.com/assets/embed.js"></script><div data-badge-details="right" data-badge-type="large-donut" data-altmetric-id="173424589" data-condensed="true" data-hide-no-mentions="true" class="altmetric-embed"></div> <p> <figure id="figure-featured-on-science-and-technology-daily"> <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Featured on Science and Technology Daily" srcset=" /publication/language2025nhb/kjrb_hu_ad30fc532e3c561e.webp 400w, /publication/language2025nhb/kjrb_hu_17fe18b6e0431f77.webp 760w, /publication/language2025nhb/kjrb_hu_bb3a102b2ff9fb5.webp 1200w" src="https://yzhu.io/publication/language2025nhb/kjrb_hu_ad30fc532e3c561e.webp" width="457" height="649" loading="lazy" data-zoomable /></div> </div><figcaption> Featured on Science and Technology Daily </figcaption></figure> <figure id="figure-featured-on-china-science-daily"> <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Featured on SFeatured on China Science Daily" srcset=" /publication/language2025nhb/zgkxb_hu_4c65033c0cff94a0.webp 400w, /publication/language2025nhb/zgkxb_hu_81db6affb71c33a0.webp 760w, /publication/language2025nhb/zgkxb_hu_75ea0eb170aef938.webp 1200w" src="https://yzhu.io/publication/language2025nhb/zgkxb_hu_4c65033c0cff94a0.webp" width="531" height="760" loading="lazy" data-zoomable /></div> </div><figcaption> Featured on China Science Daily </figcaption></figure> <figure id="figure-featured-on-peking-university"> <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Featured on Peking University" srcset=" /publication/language2025nhb/pku_hu_63bb1d2df12e8193.webp 400w, /publication/language2025nhb/pku_hu_2bbe0a2d411963b6.webp 760w, /publication/language2025nhb/pku_hu_e336c1181cdc5dfc.webp 1200w" src="https://yzhu.io/publication/language2025nhb/pku_hu_63bb1d2df12e8193.webp" width="760" height="229" loading="lazy" data-zoomable /></div> </div><figcaption> Featured on Peking University </figcaption></figure> </p>[CogSci25] Probing and Inducing Combinational Creativity in Vision-Language Modelshttps://yzhu.io/publication/creativity2025cogsci/Thu, 17 Apr 2025 00:00:00 +0000https://yzhu.io/publication/creativity2025cogsci/