[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-fair-calib-icml-2026-dllm-4-bit":3,"topics-all":36,"news-related-4eadd896-8c48-48d0-81ee-3d1ddf9a25d6":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"4eadd896-8c48-48d0-81ee-3d1ddf9a25d6","FAIR-Calib 把扩散大语言模型拉进 4-bit 量化时代，ICML 2026 接收","扩散大语言模型（dLLM）用迭代去噪一次性生成整段文本，在速度上让自回归模型压力倍增。但 dLLM 有个独特难题：token 一旦\"写定\"就锁死，量化噪声容易把\"边界\"判断彻底推反，错误会永久放大。ICML 2026 接收的 FAIR-Calib 框架正为此而生，把校准拆成两阶段：先用全精度教师对每个位置做先验探针，融合\"边界命中率 + 掩码阶段可靠性\"估计位置先验；再以离策略、按层的方式做加权隐状态 MSE 校准，全程无需昂贵的端到端扩散 rollout。理论上，加权目标等价于输出 KL 散度的代理；实验上，LLaDA 与 Dream 在 W4A4 配置下，FAIR-Calib 把边界翻转和提交后失配都压到 SOTA 之下。三点观察：（1）dLLM 的\"边写边看\"让训练-推理失配比 AR 模型更致命，错误会级联放大；（2）\"保护边界判断\"的思路可反哺 AR 模型的推测解码，判断\"该不该写\"比单纯追吞吐量更难也更有价值；（3）当 dLLM 跑进端侧、嵌入 RAG 流水线，4-bit 量化是必选项，FAIR-Calib 这类工作是把 dLLM 真正推向生产的关键拼图。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.06547","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"0a93ec8e-ea39-4693-81de-563ca8c173f7","inference",{"id":18,"name":19,"slug":19,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":21,"name":22,"slug":22,"description":13,"color":13},"b49648f9-963e-4082-8684-3d085b7358fe","quantization",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"00bc63fc-abd7-4bbd-9b22-297f8d2dda4c","en","FAIR-Calib brings diffusion LLMs into the 4-bit era (ICML)","Diffusion large language models (dLLMs) use iterative denoising to generate text in one shot, putting pressure on autoregressive models in terms of speed. But dLLMs have a unique difficulty: once a token is \"written in\" it is locked, and quantization noise easily pushes \"boundary\" judgments in the opposite direction, with errors being permanently amplified. The FAIR-Calib framework, accepted at ICML 2026, was born for this. It splits calibration into two stages: first, a full-precision teacher probes each position, fusing \"boundary hit rate + mask-stage reliability\" to estimate a position prior; then off-policy, layer-wise weighted hidden-state MSE calibration, all without expensive end-to-end diffusion rollouts. Theoretically, the weighted objective is equivalent to a proxy for the output KL divergence; experimentally, on LLaDA and Dream under the W4A4 configuration, FAIR-Calib pushes both boundary flipping and post-commit mismatch below SOTA. Three observations: (1) dLLM's \"write-as-you-look\" makes the training-inference mismatch more lethal than in AR models, with errors cascading; (2) the \"protect boundary judgment\" line of thinking can also feed back into AR models' speculative decoding, judging \"should it be written\" is harder and more valuable than simply chasing throughput; (3) when dLLMs run on device and are embedded in RAG pipelines, 4-bit quantization is a must, and works like FAIR-Calib are the key puzzle pieces to truly push dLLMs into production.","fair-calib-icml-2026-dllm-4-bit","2026-06-09T10:00:00Z","2026-06-09T10:13:13.237929Z","2026-08-19T02:08:40.142862Z",true,"agent",246,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"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":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"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":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"4d36e54d-ca37-4d34-b8d9-74ebc25762cf","PACE:递归状态量化损失主因是舍入频率","pace-four-bit-recurrent-state-quantization","2026-10-23T01:10:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"be76fca7-bc02-4a76-a58f-17a661b82b60","SparPR:消费级显卡的KV缓存回收术","sparpr-kv-cache-recovery-consumer-gpu","2026-10-22T01:20:00+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"713ebd28-7abc-4664-acd5-8ba7c6b50d97","扩散 LLM 能否 scale?Mercury 3 用 40 倍规模和 1M 上下文作答","mercury-3-diffusion-scaling","2026-10-19T23:09:33+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"ab1e6bdf-9433-41f0-be4d-cc0f78523ac2","SonicBoom v0.0.3:一个 .so 干掉手工调优","sonicboom-v003-mlir-compiler","2026-10-19T09:03:05+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"5c1d994e-4baf-41ae-a57d-33411a8981b5","KAIST KV4-RL:INT4量化KV缓存,RL训练rollout提速1.8倍","kv4-rl-int4-kv-cache-rlvr-rollout","2026-10-15T19:11:53+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"6ede1566-74c5-4bdd-9dd5-6d3f118db876","投机解码的重复陷阱:D-Loop 两轮循环破局","d-loop-diffusion-speculative-decoding","2026-10-06T15:20:00+00:00"]