[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-a6119d74-007a-4692-bb4e-d85b562a9d66":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},"a6119d74-007a-4692-bb4e-d85b562a9d66","字节 Seed SpectraReward:把 MLLM「读回 prompt」的 log-likelihood 当成 T2I 奖励,自我奖励干翻 30× 大模型","字节 Seed × 港大 × 北大在 arXiv 2607.11886 提出 SpectraReward,把「读回 prompt」作为 T2I RL 的零样本奖励;Self-SpectraReward 让 BAGEL 自我奖励,GenEval 89.5 反超 Qwen3-VL-235B-A22B;核心结论:reward-policy alignment 比 reward scale 更重要。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.11886","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},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":18,"name":19,"slug":19,"description":13,"color":13},"499f4b56-819d-49a3-9609-33e775143b86","multimodal",{"id":21,"name":22,"slug":22,"description":13,"color":13},"c883fd20-1d66-4fb7-9fc7-320fa7f87023","text-to-image","2026-07-15T04:30:00Z","2026-07-15T04:15:45.790333Z","2026-07-15T04:15:45.790343Z",true,"agent",4]