\n\t<a id=\"🧩-limix-2-towards-general-structured-data-intelligence\" class=\"block pr-1.5 text-lg md:absolute md:p-1.5 md:opacity-0 md:group-hover:opacity-100 md:right-full\" href=\"#🧩-limix-2-towards-general-structured-data-intelligence\" rel=\"nofollow\">\n\t\t<span class=\"header-link\"><svg class=\"text-gray-500 hover:text-black dark:hover:text-gray-200 w-4\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" aria-hidden=\"true\" role=\"img\" width=\"1em\" height=\"1em\" preserveAspectRatio=\"xMidYMid meet\" viewBox=\"0 0 256 256\"><path d=\"M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z\" fill=\"currentColor\"></path></svg></span>\n\t</a>\n\t<span>\n\t\t🧩 <strong>LimiX-2: Towards General Structured-Data Intelligence</strong>\n\t</span>\n</h1>\n<p><strong>One pretrained model. Multiple structured-data tasks. #1 across three major tabular benchmarks.</strong><br>LimiX-2 is a pretrained foundation model for structured data that can support<br>🎯 <strong>Classification</strong><br>📈 <strong>Regression</strong><br>🧩 <strong>Missing-value imputation</strong><br>🔗 <strong>Causal skeleton recovery</strong><br>— with <strong>no task-specific parameter updates</strong> for downstream prediction tasks.</p>\n<h1 class=\"relative group flex items-baseline\">\n\t<a id=\"🏆-1-across-all-three-benchmarks\" class=\"block pr-1.5 text-lg md:absolute md:p-1.5 md:opacity-0 md:group-hover:opacity-100 md:right-full\" href=\"#🏆-1-across-all-three-benchmarks\" rel=\"nofollow\">\n\t\t<span class=\"header-link\"><svg class=\"text-gray-500 hover:text-black dark:hover:text-gray-200 w-4\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" aria-hidden=\"true\" role=\"img\" width=\"1em\" height=\"1em\" preserveAspectRatio=\"xMidYMid meet\" viewBox=\"0 0 256 256\"><path d=\"M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z\" fill=\"currentColor\"></path></svg></span>\n\t</a>\n\t<span>\n\t\t🏆 #1 across all three benchmarks\n\t</span>\n</h1>\n<p><strong>LimiX-2 takes the top spot on all three broad tabular benchmarks we evaluate:</strong><br>🏆 TabArena — 1935 Elo<br>🏆 TALENT — 1506 Elo<br>🏆 BCCO — 1432 Elo<br><strong>LimiX-2 ranks #1</strong> overall across all three, ahead of leading tabular foundation models and strong dataset-specific systems.<br>And the gains continue as we scale the model from <strong>12.5M → 406.2M</strong> parameters: performance improves consistently across all five evaluated scaling series, with no clear sign of saturation within the measured range.<br>So how can one pretrained model handle such different structured-data problems?</p>\n<h2 class=\"relative group flex items-baseline\">\n\t<a id=\"a-table-is-more-than-a-target-column\" class=\"block pr-1.5 text-lg md:absolute md:p-1.5 md:opacity-0 md:group-hover:opacity-100 md:right-full\" href=\"#a-table-is-more-than-a-target-column\" rel=\"nofollow\">\n\t\t<span class=\"header-link\"><svg class=\"text-gray-500 hover:text-black dark:hover:text-gray-200 w-4\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" aria-hidden=\"true\" role=\"img\" width=\"1em\" height=\"1em\" preserveAspectRatio=\"xMidYMid meet\" viewBox=\"0 0 256 256\"><path d=\"M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z\" fill=\"currentColor\"></path></svg></span>\n\t</a>\n\t<span>\n\t\tA table is more than a target column.\n\t</span>\n</h2>\n<p>Most tabular foundation models are organized around one question:<br>given ( x ), predict ( y ).<br>LimiX-2 takes a broader view:<br><strong>Can a model learn the relationships among variables in a table, so that different unknown quantities can be inferred from different observed ones?</strong><br>We introduce <strong>Contextual Mechanism Networks (CMNs)</strong>, a new paradigm that shifts structured-data in-context learning from target-centric prediction toward context-dependent joint modeling.<br>Instead of focusing only on<br><span class=\"katex-display\"><span class=\"katex\"><span class=\"katex-mathml\"><math xmlns=\"http://www.w3.org/1998/Math/MathML\" display=\"block\"><mrow><mi>p</mi><mo stretchy=\"false\">(</mo><mi>y</mi><mo>∣</mo><mi>x</mi><mo separator=\"true\">,</mo><msub><mi>D</mi><mrow><mi mathvariant=\"normal\">c</mi><mi mathvariant=\"normal\">o</mi><mi mathvariant=\"normal\">n</mi><mi mathvariant=\"normal\">t</mi><mi mathvariant=\"normal\">e</mi><mi mathvariant=\"normal\">x</mi><mi mathvariant=\"normal\">t</mi></mrow></msub><mo stretchy=\"false\">)</mo></mrow>p(y \\mid x, D_{\\mathrm{context}})</math></span><span class=\"katex-html\" aria-hidden=\"true\"><span class=\"base\"><span class=\"strut\" style=\"height:1em;vertical-align:-0.25em;\"></span><span class=\"mord mathnormal\">p</span><span class=\"mopen\">(</span><span class=\"mord mathnormal\" style=\"margin-right:0.03588em;\">y</span><span class=\"mspace\" style=\"margin-right:0.2778em;\"></span><span class=\"mrel\">∣</span><span class=\"mspace\" style=\"margin-right:0.2778em;\"></span></span><span class=\"base\"><span class=\"strut\" style=\"height:1em;vertical-align:-0.25em;\"></span><span class=\"mord mathnormal\">x</span><span class=\"mpunct\">,</span><span class=\"mspace\" style=\"margin-right:0.1667em;\"></span><span class=\"mord\"><span class=\"mord mathnormal\" style=\"margin-right:0.02778em;\">D</span><span class=\"msupsub\"><span class=\"vlist-t vlist-t2\"><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.2806em;\"><span style=\"top:-2.55em;margin-left:-0.0278em;margin-right:0.05em;\"><span class=\"pstrut\" style=\"height:2.7em;\"></span><span class=\"sizing reset-size6 size3 mtight\"><span class=\"mord mtight\"><span class=\"mord mtight\"><span class=\"mord mathrm mtight\">context</span></span></span></span></span></span><span class=\"vlist-s\">​</span></span><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.15em;\"><span></span></span></span></span></span></span><span class=\"mclose\">)</span></span></span></span></span><br>CMNs aim to capture the broader dependency structure behind<br><span class=\"katex-display\"><span class=\"katex\"><span class=\"katex-mathml\"><math xmlns=\"http://www.w3.org/1998/Math/MathML\" display=\"block\"><mrow><mi>p</mi><mo stretchy=\"false\">(</mo><mi>x</mi><mo separator=\"true\">,</mo><mi>y</mi><mo>∣</mo><msub><mi>D</mi><mrow><mi mathvariant=\"normal\">c</mi><mi mathvariant=\"normal\">o</mi><mi mathvariant=\"normal\">n</mi><mi mathvariant=\"normal\">t</mi><mi mathvariant=\"normal\">e</mi><mi mathvariant=\"normal\">x</mi><mi mathvariant=\"normal\">t</mi></mrow></msub><mo stretchy=\"false\">)</mo></mrow>p(x,y \\mid D_{\\mathrm{context}})</math></span><span class=\"katex-html\" aria-hidden=\"true\"><span class=\"base\"><span class=\"strut\" style=\"height:1em;vertical-align:-0.25em;\"></span><span class=\"mord mathnormal\">p</span><span class=\"mopen\">(</span><span class=\"mord mathnormal\">x</span><span class=\"mpunct\">,</span><span class=\"mspace\" style=\"margin-right:0.1667em;\"></span><span class=\"mord mathnormal\" style=\"margin-right:0.03588em;\">y</span><span class=\"mspace\" style=\"margin-right:0.2778em;\"></span><span class=\"mrel\">∣</span><span class=\"mspace\" style=\"margin-right:0.2778em;\"></span></span><span class=\"base\"><span class=\"strut\" style=\"height:1em;vertical-align:-0.25em;\"></span><span class=\"mord\"><span class=\"mord mathnormal\" style=\"margin-right:0.02778em;\">D</span><span class=\"msupsub\"><span class=\"vlist-t vlist-t2\"><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.2806em;\"><span style=\"top:-2.55em;margin-left:-0.0278em;margin-right:0.05em;\"><span class=\"pstrut\" style=\"height:2.7em;\"></span><span class=\"sizing reset-size6 size3 mtight\"><span class=\"mord mtight\"><span class=\"mord mtight\"><span class=\"mord mathrm mtight\">context</span></span></span></span></span></span><span class=\"vlist-s\">​</span></span><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.15em;\"><span></span></span></span></span></span></span><span class=\"mclose\">)</span></span></span></span></span><br>LimiX-2 instantiates this idea with <strong>Context-Conditional Masked Modeling (CCMM)</strong>.<br>During pretraining, different variables are masked under different observation patterns, turning the same table into many conditional prediction problems. Rather than learning only how to predict one designated target, the model learns to infer different variables from different available evidence.<br>LimiX-2 is pretrained exclusively on synthetic datasets generated from diverse <strong>structural causal models (SCMs)</strong>, spanning different graph structures, functional mechanisms, distributions, and observation processes.<br>This broader training objective gives a single pretrained model a unified basis for classification, regression, and missing-value reconstruction.<br>Beyond predictive performance, we also find that LimiX-2's learned feature attention contains structural information that can be used for causal skeleton recovery—suggesting that learning conditional relationships across variables can capture structure beyond a single supervised target.<br>This points to a broader possibility:<br><strong>structured-data foundation models may move beyond predicting predefined targets toward learning reusable mechanisms of how variables relate and interact.</strong><br>** A table is more than a target column. Prediction may be only the beginning.**<br>The next question is:<br><strong>How far can general structured-data intelligence scale?</strong><br><strong>LimiX-2 is just the beginning. Follow the project as we push toward larger models, broader capabilities, and more general structured-data intelligence.</strong> 🚀<br>📄 Paper — <a href=\"https://arxiv.org/abs/2609.17488\" rel=\"nofollow\">https://arxiv.org/abs/2609.17488</a><br>💻 Code — <a href=\"https://github.com/limix-ldm-ai/LimiX\" rel=\"nofollow\">https://github.com/limix-ldm-ai/LimiX</a><br>🤗 Model — <a href=\"https://huggingface.co/stable-ai/LimiX-2\">https://huggingface.co/stable-ai/LimiX-2</a><br>Reproductions, independent evaluations, integrations, and feedback are very welcome.</p>\n","updatedAt":"2026-09-17T08:45:47.064Z","author":{"_id":"63440a1be01a38440ef25daa","avatarUrl":"/avatars/622e8ca69f1867be7932d03b91eaf6e7.svg","fullname":"Xingxuan Zhang","name":"xuange","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8071808218955994},"editors":["xuange"],"editorAvatarUrls":["/avatars/622e8ca69f1867be7932d03b91eaf6e7.svg"],"reactions":[],"isReport":false}},{"id":"6aabb345780948af584faeed","author":{"_id":"6aaa9d95371ff13a34ea449b","avatarUrl":"/avatars/51a3a3452f78c5624f442240f813db82.svg","fullname":"CC","name":"Tatsumi007","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"createdAt":"2026-09-17T09:30:45.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Great work on general structured‑data intelligence! Shifting from target‑centric prediction to joint mechanism‑oriented modeling looks like a promising direction for tabular foundation models. Impressive results across TabArena, TALENT and BCCO benchmarks. Really appreciate that the model also shows causal skeleton recovery capability beyond pure prediction performance. Looking forward to seeing further real‑world validations!","html":"<p>Great work on general structured‑data intelligence! Shifting from target‑centric prediction to joint mechanism‑oriented modeling looks like a promising direction for tabular foundation models. Impressive results across TabArena, TALENT and BCCO benchmarks. Really appreciate that the model also shows causal skeleton recovery capability beyond pure prediction performance. Looking forward to seeing further real‑world validations!</p>\n","updatedAt":"2026-09-17T09:30:45.920Z","author":{"_id":"6aaa9d95371ff13a34ea449b","avatarUrl":"/avatars/51a3a3452f78c5624f442240f813db82.svg","fullname":"CC","name":"Tatsumi007","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8497351408004761},"editors":["Tatsumi007"],"editorAvatarUrls":["/avatars/51a3a3452f78c5624f442240f813db82.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2609.17488","authors":[{"_id":"6aaa0287f6668522fbb08046","user":{"_id":"63440a1be01a38440ef25daa","avatarUrl":"/avatars/622e8ca69f1867be7932d03b91eaf6e7.svg","isPro":false,"fullname":"Xingxuan Zhang","user":"xuange","type":"user","name":"xuange"},"name":"Xingxuan Zhang","status":"claimed_verified","statusLastChangedAt":"2026-09-16T16:45:04.225Z","hidden":false},{"_id":"6aaa0287f6668522fbb08047","name":"Gang Ren","hidden":false},{"_id":"6aaa0287f6668522fbb08048","name":"Hao Yuan","hidden":false},{"_id":"6aaa0287f6668522fbb08049","name":"Hao Zou","hidden":false},{"_id":"6aaa0287f6668522fbb0804a","name":"Hongze Tan","hidden":false},{"_id":"6aaa0287f6668522fbb0804b","name":"Hui Wang","hidden":false},{"_id":"6aaa0287f6668522fbb0804c","name":"Jianhao Song","hidden":false},{"_id":"6aaa0287f6668522fbb0804d","name":"Jiansheng Li","hidden":false},{"_id":"6aaa0287f6668522fbb0804e","name":"Jiayao Zhang","hidden":false},{"_id":"6aaa0287f6668522fbb0804f","name":"Jinghan Zhang","hidden":false},{"_id":"6aaa0287f6668522fbb08050","name":"Kaifang Li","hidden":false},{"_id":"6aaa0287f6668522fbb08051","name":"Lang Mo","hidden":false},{"_id":"6aaa0287f6668522fbb08052","name":"Li Mao","hidden":false},{"_id":"6aaa0287f6668522fbb08053","name":"Mingchao Hao","hidden":false},{"_id":"6aaa0287f6668522fbb08054","name":"Nuo Xu","hidden":false},{"_id":"6aaa0287f6668522fbb08055","name":"Rui Ding","hidden":false},{"_id":"6aaa0287f6668522fbb08056","name":"Ruiji Zhang","hidden":false},{"_id":"6aaa0287f6668522fbb08057","name":"Shuyang Li","hidden":false},{"_id":"6aaa0287f6668522fbb08058","name":"Siyu Mei","hidden":false},{"_id":"6aaa0287f6668522fbb08059","name":"Tianyang Zhang","hidden":false},{"_id":"6aaa0287f6668522fbb0805a","name":"Weiyang Mu","hidden":false},{"_id":"6aaa0287f6668522fbb0805b","name":"Yancheng Dong","hidden":false},{"_id":"6aaa0287f6668522fbb0805c","name":"Yongxian Wei","hidden":false},{"_id":"6aaa0287f6668522fbb0805d","name":"Yuan Xue","hidden":false},{"_id":"6aaa0287f6668522fbb0805e","name":"Yuanrui Wang","hidden":false},{"_id":"6aaa0287f6668522fbb0805f","name":"Yue He","hidden":false},{"_id":"6aaa0287f6668522fbb08060","name":"Zijia Yang","hidden":false},{"_id":"6aaa0287f6668522fbb08061","name":"Ziyun Li","hidden":false},{"_id":"6aaa0287f6668522fbb08062","name":"Dongzhe Li","hidden":false},{"_id":"6aaa0287f6668522fbb08063","name":"Fuqiang Wang","hidden":false},{"_id":"6aaa0287f6668522fbb08064","name":"Jiandong Liu","hidden":false},{"_id":"6aaa0287f6668522fbb08065","name":"Jiawei Chen","hidden":false},{"_id":"6aaa0287f6668522fbb08066","name":"Jiaxin Du","hidden":false},{"_id":"6aaa0287f6668522fbb08067","name":"Kaijie Cheng","hidden":false},{"_id":"6aaa0287f6668522fbb08068","name":"Kehan Li","hidden":false},{"_id":"6aaa0287f6668522fbb08069","name":"Lei Sun","hidden":false},{"_id":"6aaa0287f6668522fbb0806a","name":"Linjun Zhou","hidden":false},{"_id":"6aaa0287f6668522fbb0806b","name":"Ningbo Dai","hidden":false},{"_id":"6aaa0287f6668522fbb0806c","name":"Qi Wang","hidden":false},{"_id":"6aaa0287f6668522fbb0806d","name":"Renzhe Xu","hidden":false},{"_id":"6aaa0287f6668522fbb0806e","name":"Shaoxing Du","hidden":false},{"_id":"6aaa0287f6668522fbb0806f","name":"Shumeng Yang","hidden":false},{"_id":"6aaa0287f6668522fbb08070","name":"Wang Lu","hidden":false},{"_id":"6aaa0287f6668522fbb08071","name":"Wenjing Chu","hidden":false},{"_id":"6aaa0287f6668522fbb08072","name":"Xiannan Huang","hidden":false},{"_id":"6aaa0287f6668522fbb08073","name":"Xiaoyu Lin","hidden":false},{"_id":"6aaa0287f6668522fbb08074","name":"Xing Ai","hidden":false},{"_id":"6aaa0287f6668522fbb08075","name":"Xinyan Han","hidden":false},{"_id":"6aaa0287f6668522fbb08076","name":"Xuanyue Li","hidden":false},{"_id":"6aaa0287f6668522fbb08077","name":"Xuanyue Su","hidden":false},{"_id":"6aaa0287f6668522fbb08078","name":"Xukun Zhang","hidden":false},{"_id":"6aaa0287f6668522fbb08079","name":"Yan Lu","hidden":false},{"_id":"6aaa0287f6668522fbb0807a","name":"Yaxin Zhang","hidden":false},{"_id":"6aaa0287f6668522fbb0807b","name":"Yi Qin","hidden":false},{"_id":"6aaa0287f6668522fbb0807c","name":"Yifei Huang","hidden":false},{"_id":"6aaa0287f6668522fbb0807d","name":"Yihan Xu","hidden":false},{"_id":"6aaa0287f6668522fbb0807e","name":"Yongle Lv","hidden":false},{"_id":"6aaa0287f6668522fbb0807f","name":"Yuanyuan Jiang","hidden":false},{"_id":"6aaa0287f6668522fbb08080","name":"Yushan Han","hidden":false},{"_id":"6aaa0287f6668522fbb08081","name":"Peng Cui","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/63440a1be01a38440ef25daa/82Td574Ji7ShkZWIF58uf.mp4"],"publishedAt":"2026-09-15T00:00:00.000Z","submittedOnDailyAt":"2026-09-17T00:00:00.000Z","title":"LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence","submittedOnDailyBy":{"_id":"63440a1be01a38440ef25daa","avatarUrl":"/avatars/622e8ca69f1867be7932d03b91eaf6e7.svg","isPro":false,"fullname":"Xingxuan Zhang","user":"xuange","type":"user","name":"xuange"},"summary":"We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX-2 adopts the Contextual Mechanism Networks (CMNs) paradigm and is pretrained with Context-Conditional Masked Modeling (CCMM). CMNs shifts the organizing principle of in-context learning from target-centric prediction to mechanism-oriented joint modeling. Rather than centering the network on the p(y mid x, D_{context}) objective of conventional tabular PFNs, it is designed around learning p(x, y mid D_{context}), a context-dependent representation of the joint structure underlying data generation. Pretraining uses synthetic datasets generated by structural causal models (SCMs) spanning diverse graph structures, functional mechanisms, and observation processes. Evaluations on TabArena, TALENT, and BCCO show that LimiX-2 outperforms current dataset-specific models and tabular foundation models. Beyond predictive performance, the CMN paradigm also promotes causal awareness in LimiX-2: its feature attention encodes direct causal relationships, enabling accurate causal skeleton recovery.","upvotes":84,"discussionId":"6aaa0288f6668522fbb08082","projectPage":"https://www.limix.ai/","githubRepo":"https://github.com/limix-ldm-ai/LimiX","githubRepoAddedBy":"user","githubStars":4186,"organization":{"_id":"6911d3dc57d393d3cfe628bf","name":"stable-ai","fullname":"Stable AI","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68aa772042ec888900da6a6b/ykANVIVEnhVZ1fdsEz7BQ.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6698a1efbf3edea3110a6e66","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6698a1efbf3edea3110a6e66/WzwIu_8NKEcN10CEw8G8O.jpeg","isPro":false,"fullname":"Weiqi Feng","user":"Fengwq22","type":"user"},{"_id":"63440a1be01a38440ef25daa","avatarUrl":"/avatars/622e8ca69f1867be7932d03b91eaf6e7.svg","isPro":false,"fullname":"Xingxuan Zhang","user":"xuange","type":"user"},{"_id":"635e68c40ddaddda094b05db","avatarUrl":"/avatars/5a0f447ded1ecf34321c0e7db2e9f23e.svg","isPro":false,"fullname":"Renzhe Xu","user":"Windzrx","type":"user"},{"_id":"64eeebde2cf03e20ace48d2a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/PqiTx7RVeBuRtX5EKy22x.jpeg","isPro":false,"fullname":"dushaoxing","user":"dushaoxing","type":"user"},{"_id":"64afa2d0e90648db9ae312a1","avatarUrl":"/avatars/94bf684f8c9c48b0605660237ee62f8b.svg","isPro":false,"fullname":"Taylor Mei","user":"taylormei","type":"user"},{"_id":"64f01e43bae933568b81b1ed","avatarUrl":"/avatars/a88cd5866a49707b94a41aaffc3c2e45.svg","isPro":false,"fullname":"yhxu","user":"yhxu022","type":"user"},{"_id":"660aa3852d0769b9c675ece5","avatarUrl":"/avatars/3dc65a24bea1037db106f9f9f8e7e182.svg","isPro":false,"fullname":"haomingchao","user":"mingchaocc","type":"user"},{"_id":"653cb2ae885338b011bcb1f8","avatarUrl":"/avatars/49b6eeefdec1d27eb14bf288407fbc84.svg","isPro":false,"fullname":"ericwang","user":"erisura","type":"user"},{"_id":"64cb50a08a16b1748ffe695a","avatarUrl":"/avatars/3233491124da756d4d90553cd14c7afd.svg","isPro":false,"fullname":"Yuan Xue","user":"XueY-L","type":"user"},{"_id":"663b5baee6257fa86a2a7267","avatarUrl":"/avatars/6bd26c684cd40a1bf5b73a604c6ee0e1.svg","isPro":false,"fullname":"MoLang","user":"Jacksooooff","type":"user"},{"_id":"6aaa9d95371ff13a34ea449b","avatarUrl":"/avatars/51a3a3452f78c5624f442240f813db82.svg","isPro":false,"fullname":"CC","user":"Tatsumi007","type":"user"},{"_id":"66e90532037ce31eb4372711","avatarUrl":"/avatars/ee5162e75965645f9040935b58887d4e.svg","isPro":false,"fullname":"Olivia Huang","user":"Olivia802","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":1,"organization":{"_id":"6911d3dc57d393d3cfe628bf","name":"stable-ai","fullname":"Stable AI","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68aa772042ec888900da6a6b/ykANVIVEnhVZ1fdsEz7BQ.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2609/2609.17488.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2609.17488 in a dataset README.md to link it from this page.

Add this paper to a collection to link it from this page.