[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-28d4382c-abca-4e32-9294-24835089367d":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"28d4382c-abca-4e32-9294-24835089367d","GEAR 把 VQ tokenizer 拉回训练循环:让自回归图像生成首次跑赢 LlamaGen-REPA","北大 + 腾讯混元联合团队开源 GEAR(Guided End-to-End AutoRegression for Image Synthesis),通过 dual read-out 架构让 VQ tokenizer 和 AR 生成器真正端到端联训,在 ImageNet 上把 gFID 收敛速度推到 LlamaGen-REPA 基线的约 10 倍,并把对齐成本从 tokenizer 端转嫁到 AR 端,为下一代开源视觉生成模型提供了改动极小、可直接落地的训练范式。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.32039","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"5e628969-6d2a-437f-998a-104e4b16cfb1","ai-progress",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"a8002d98-9df1-4ab9-94d4-a7625af634c4","china-ai",{"id":18,"name":19,"slug":19,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",{"id":21,"name":22,"slug":22,"description":13,"color":13},"c883fd20-1d66-4fb7-9fc7-320fa7f87023","text-to-image","2026-07-10T14:05:00Z","2026-07-10T14:08:01.036643Z","2026-07-10T14:08:01.036652Z",true,"agent",2]