[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-longbanana-multi-reference-image-synthesis-benchmark":3,"topics-all":38,"news-related-bff1ec03-4e40-4d63-be35-82da33948969":57},{"id":4,"title":5,"summary":6,"content":7,"original_url":8,"source_id":9,"tags":10,"translations":24,"news_slug":31,"published_at":32,"created_at":33,"modified_at":34,"is_published":35,"publish_type":36,"image_url":14,"view_count":37},"bff1ec03-4e40-4d63-be35-82da33948969","图像生成的长上下文考试:32张参考图拼一张图","华南师大、CMU 等机构联合 KlingAI Research 发布 LongBanana 基准:90 个多参考图像合成任务,每题约 32 张参考图、20 项约束,共 4,670 条专家检查项,已标注被 NeurIPS 2026 接收。RPR 工作流抬高平均分,却在部分框架上拉低通过率。","文生图这两年把「好看」卷出了新高度,但换一种考法就不一定了:一次给 32 张参考图,要求找出散落各处的证据、绑到正确的对象上、再满足 20 项约束,最后拼成一张连贯的图。华南师大、滑铁卢、Vector、CMU、清华、港科大、港大等机构联合 KlingAI Research 发布的 LongBanana 基准做的就是这件事,多位作者在 KlingAI Research 实习期间完成工作,项目页标注已被 NeurIPS 2026 接收。\n\n## 考的是「查证」,不是「像不像」\n\nLongBanana 收录 90 个任务,按 3×3 分类组织:场景合成、视觉外观、参考推理三大套件,每套件三个子类、每子类十题。每题平均配 32 张参考图、20 项约束、50 个评测点,合计 4,670 条专家逐条写出的原子检查项。出题走逆向构造:专家先从真实场景建一张实体-关系图,再让参考图清单、合成指令和评分标准都对齐到这张图上。至少 30 道题埋了两个以上「硬负样本」——长得像、用上去就错的干扰图,专治模型想当然。作者称这是首个由专家设计并专家验证的长上下文多参考图像合成基准。\n\n## 分数怎么算才可信\n\n评测同样围绕实体-关系图展开:节点、边和全图义务被逐条转成检查项,分内容保真、关系绑定、全局约束满足三类;三位评审分别负责这三类,可选 OCR、计数、布局、身份工具辅助,每个判断都要先留证据记录再聚合,按 0\u002F1\u002F2 三档打分。人工审核池覆盖 90 题 × 10 种生成条件,共 900 张输出、46,700 条已复核标签;15% 的双标子集完全一致率 89.4%,二次加权 kappa 0.83。这套流程把「图好不好」变成了可逐条审计的证据链,而不是一句「看起来不错」。\n\n## agent 反而暴露了短板\n\n配套的 LongBanana-Gen 给出工作流层面的答案:RPR,把 ReAct、计划-执行与反思串起来——先检索证据,再组织生成,发现绑定错误就回头修。但实验结论并不一边倒:极简 agent 工作流就能压过直接生成,RPR 也在报告的各框架上抬高了 checklist 平均分;可到了任务通过率上,OpenCode 和 Hermes-Agent 反而下降。换句话说,推理链越长,引用错证据的机会也越多,更会推理不等于绑对参考。\n\n## 所以呢\n\n图像生成的下一个瓶颈不在像素,在证据。当输入从「一句提示」变成「一堆材料」,考验的就是检索、绑定与核查能力,这正是长上下文多模态最缺的基建。数据集已上架 Hugging Face(Kwai-Kolors\u002FLongBanana),代码与数据在项目页公开。下次再看到「文生图屠榜」,不妨先问一句:它能在 32 张参考图里,找对那张真正该用的吗?","https:\u002F\u002Farxiv.org\u002Fabs\u002F2611.06856","7437aeb9-930c-4866-a2e9-48003c1a792b",[11,15,18,21],{"id":12,"name":13,"slug":13,"description":14,"color":14},"6ad31a14-c0da-42df-81fd-564281f768db","agentic-ai",null,{"id":16,"name":17,"slug":17,"description":14,"color":14},"120fa59a-ff6f-4537-9bf5-f818df636a0e","benchmark",{"id":19,"name":20,"slug":20,"description":14,"color":14},"499f4b56-819d-49a3-9609-33e775143b86","multimodal",{"id":22,"name":23,"slug":23,"description":14,"color":14},"c883fd20-1d66-4fb7-9fc7-320fa7f87023","text-to-image",[25],{"id":26,"lang":27,"title":28,"summary":29,"content":30},"b94d40c4-bb6a-4c71-864e-c85edf039ff0","en","LongBanana: 32 reference images, 4,670 checks, one image","LongBanana: expert-verified benchmark, 90 tasks, ~32 reference images each, 4,670 atomic checks. RPR agents lift scores but cut pass rates on two harnesses.","Text-to-image models have gotten very good at looking plausible. LongBanana, released by researchers from South China Normal University, Waterloo, the Vector Institute, CMU, Tsinghua, HKUST and HKU together with KlingAI Research, tests a harder skill: given about 32 reference images per task, find the scattered evidence, bind it to the right entities, satisfy 20 constraints, and compose one coherent image. Several authors did the work during internships at KlingAI Research, and the project page marks the benchmark accepted to NeurIPS 2026.\n\n## What the exam tests\n\nLongBanana contains 90 tasks in a 3-by-3 taxonomy — Scene Composition, Visual Appearance and Reference Reasoning — with ten cases per category. Each task carries about 32 reference images, 20 constraints and 50 evaluation items, for 4,670 expert-specified atomic checks in total. Cases are reverse-constructed: experts start from a realistic scenario, build an entity-relation graph, and align reference inventories, synthesis instructions and evaluation criteria to that same graph. At least 30 cases embed two or more hard negatives — visually convincing distractors that are simply wrong to use. The authors call it the first expert-designed and expert-verified benchmark for long-context multi-reference image synthesis.\n\n## Scores you can audit\n\nThe same graph grounds evaluation: node, edge and whole-graph obligations become checklist items for Content Fidelity, Relational Binding and Global Constraint Satisfaction. Three critics cover those three categories, with optional OCR, counting, layout and identity tools; every judgment records an evidence trace before aggregation, scored 0, 1 or 2. The human-audited pool spans 90 cases across 10 generation conditions — 900 outputs and 46,700 reviewed labels — and a 15% double-labeled subset shows 89.4% exact agreement with 0.83 quadratic weighted kappa. Image quality becomes an auditable chain of evidence rather than a vibe.\n\n## Agents expose their own weakness\n\nThe companion LongBanana-Gen framework proposes RPR — ReAct plus Plan-Exec plus Reflect — to retrieve evidence, organize generation and repair reference-grounded errors. The results cut both ways: minimal agent harnesses beat direct generation, and RPR lifts checklist averages across the reported harnesses; yet task pass rates drop for OpenCode and Hermes-Agent. Longer reasoning chains create more chances to cite the wrong evidence — more reasoning does not mean the right reference stays bound.\n\n## So what\n\nThe next bottleneck for image generation is not pixels but evidence: retrieval, binding and verification. The dataset is on Hugging Face (Kwai-Kolors\u002FLongBanana), with code and data on the project page. Next time a model \"tops the leaderboard\" on text-to-image, ask one question first: can it pick the right image out of 32 references?","longbanana-multi-reference-image-synthesis-benchmark","2026-11-05T17:05:54Z","2026-11-05T17:05:58.756653Z","2026-11-05T17:05:58.756661Z",true,"agent",76,[39,48],{"slug":40,"tag_slug":40,"title_zh":41,"title_en":42,"intro_zh":43,"intro_en":44,"id":45,"is_active":35,"created_at":46,"modified_at":47},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":49,"tag_slug":49,"title_zh":50,"title_en":51,"intro_zh":52,"intro_en":53,"id":54,"is_active":35,"created_at":55,"modified_at":56},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":58},[59,64,69,74,79,84],{"id":60,"title":61,"news_slug":62,"published_at":63},"950e298b-7e72-443b-939e-ef8ba07ee677","多模态社工攻破7个智能体:验证越多被骗越狠","multimodal-sea-social-engineering-agent-security-benchmark","2026-11-08T09:05:00+00:00",{"id":65,"title":66,"news_slug":67,"published_at":68},"643e4f3e-2ec0-47eb-b732-4d8da1b18e70","视频模型该学会追问:离线52.18%,流式只剩7.22%","askstream-proactive-asking-streaming-video","2026-11-02T01:35:00+00:00",{"id":70,"title":71,"news_slug":72,"published_at":73},"fd0e593c-bb2c-44f9-8913-16f8dcef6999","苹果8B智能体:真实iOS上追平Gemini-3.1-Pro","apple-online-rl-ui-agent-live-ios","2026-10-31T11:10:00+00:00",{"id":75,"title":76,"news_slug":77,"published_at":78},"9109e6b0-bf85-472d-abf6-ba8e31dc17c5","Co-Design 基准:七成准则过,26.4% 完整交付","co-design-bench-agent-delivery-gap","2026-10-30T05:00:00+00:00",{"id":80,"title":81,"news_slug":82,"published_at":83},"db8f2b94-8565-49fe-9fd8-08310f441161","HiSTEVE 1.0:像人一样玩我的世界,只靠屏幕和键鼠","histeve-hierarchical-vla-minecraft-agent","2026-10-26T15:13:44+00:00",{"id":85,"title":86,"news_slug":87,"published_at":88},"5be712c9-ff84-4e5a-aefa-673f880c8ed1","视频深度研究报告基准:AI排版强内容弱,最高63.3分","omnidr-bench-video-deep-research","2026-10-25T19:15:23+00:00"]