{ "id": 575223, "title": "update from ICLR 2025", "url": "/competitions/stanford-rna-3d-folding/discussion/575223", "author_name": "", "post_date": "2025-04-26T23:21:04.284905900Z", "votes": 12, "comment_count": 3, "views": 0, "content": "

\"\"
\nhttps://x.com/GabriCorso/status/1916234998417657990
\nBoltz-1x introduces inference-time steering for much higher physical quality, CUDA kernels for faster, more memory-efficient inference and training, and more!
\n\"\"

", "messages": [ { "id": "3188023", "postDate": "04/26/2025 23:21:04", "content": "

\"\"
\nhttps://x.com/GabriCorso/status/1916234998417657990
\nBoltz-1x introduces inference-time steering for much higher physical quality, CUDA kernels for faster, more memory-efficient inference and training, and more!
\n\"\"

", "rawMarkdown": "![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fc48f44e96501b9b5983d404a98ed59fb%2FSelection_999(8136).png?generation=1745709615469135&alt=media)\n\nhttps://x.com/GabriCorso/status/1916234998417657990\nBoltz-1x introduces inference-time steering for much higher physical quality, CUDA kernels for faster, more memory-efficient inference and training, and more!\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fd9ad0b8099a1f8552361bdaf5c10056c%2FSelection_999(8137).png?generation=1745709824733806&alt=media)", "votes": null }, { "id": "3188028", "postDate": "04/26/2025 23:40:11", "content": "

AI for Nucleic Acids (iclr workshop 2025)
\nhttps://ai4na-workshop.github.io/accepted/

\n

[1] On inputs to deep learning for RNA 3D structure prediction
\n[2] RNAGym: Benchmarks for RNA Fitness and Structure Prediction (secondary structure)

", "rawMarkdown": "AI for Nucleic Acids (iclr workshop 2025)\nhttps://ai4na-workshop.github.io/accepted/\n\n[1] On inputs to deep learning for RNA 3D structure prediction\n[2] RNAGym: Benchmarks for RNA Fitness and Structure Prediction (secondary structure)", "votes": null }, { "id": "3188477", "postDate": "04/27/2025 16:48:45", "content": "

May I ask if the above solution requires sufficient GPU resources? Are the GPU computing resources provided by Kaggle enough? I am a beginner and do not have enough GPU resources to train complex models.😭

", "rawMarkdown": "May I ask if the above solution requires sufficient GPU resources? Are the GPU computing resources provided by Kaggle enough? I am a beginner and do not have enough GPU resources to train complex models.😭", "votes": null }, { "id": "3188605", "postDate": "04/27/2025 23:54:50", "content": "

data generator?
\nDPLM-2: A Multimodal Diffusion Protein Language Model
\nhttps://arxiv.org/abs/2410.13782

\n

i wonder if we marginise, can we generate seq-> structure -> seq. this is similiar trick for verification in language translation

\n

\"\"

\n

https://x.com/zaixiang_zheng/status/1916311160842031433

", "rawMarkdown": "data generator?\nDPLM-2: A Multimodal Diffusion Protein Language Model\nhttps://arxiv.org/abs/2410.13782\n\ni wonder if we marginise, can we generate seq-> structure -> seq. this is similiar trick for verification in language translation\n\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2F78d0cdd21371316f4b4121fccfb36cfb%2FSelection_999(8147).png?generation=1745797958749775&alt=media)\n\nhttps://x.com/zaixiang_zheng/status/1916311160842031433", "votes": null } ], "comments": [ { "id": 3188028, "author_name": "hengck23", "author_url": "", "post_date": "04/26/2025 23:40:11", "content": "

AI for Nucleic Acids (iclr workshop 2025)
\nhttps://ai4na-workshop.github.io/accepted/

\n

[1] On inputs to deep learning for RNA 3D structure prediction
\n[2] RNAGym: Benchmarks for RNA Fitness and Structure Prediction (secondary structure)

", "votes": null, "replies": [] }, { "id": 3188477, "author_name": "yunkaiwang2", "author_url": "", "post_date": "04/27/2025 16:48:45", "content": "

May I ask if the above solution requires sufficient GPU resources? Are the GPU computing resources provided by Kaggle enough? I am a beginner and do not have enough GPU resources to train complex models.😭

", "votes": null, "replies": [] }, { "id": 3188605, "author_name": "hengck23", "author_url": "", "post_date": "04/27/2025 23:54:50", "content": "

data generator?
\nDPLM-2: A Multimodal Diffusion Protein Language Model
\nhttps://arxiv.org/abs/2410.13782

\n

i wonder if we marginise, can we generate seq-> structure -> seq. this is similiar trick for verification in language translation

\n

\"\"

\n

https://x.com/zaixiang_zheng/status/1916311160842031433

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "3188023": "![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fc48f44e96501b9b5983d404a98ed59fb%2FSelection_999(8136).png?generation=1745709615469135&alt=media)\n\nhttps://x.com/GabriCorso/status/1916234998417657990\nBoltz-1x introduces inference-time steering for much higher physical quality, CUDA kernels for faster, more memory-efficient inference and training, and more!\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fd9ad0b8099a1f8552361bdaf5c10056c%2FSelection_999(8137).png?generation=1745709824733806&alt=media)", "3188028": "AI for Nucleic Acids (iclr workshop 2025)\nhttps://ai4na-workshop.github.io/accepted/\n\n[1] On inputs to deep learning for RNA 3D structure prediction\n[2] RNAGym: Benchmarks for RNA Fitness and Structure Prediction (secondary structure)", "3188477": "May I ask if the above solution requires sufficient GPU resources? Are the GPU computing resources provided by Kaggle enough? I am a beginner and do not have enough GPU resources to train complex models.😭", "3188605": "data generator?\nDPLM-2: A Multimodal Diffusion Protein Language Model\nhttps://arxiv.org/abs/2410.13782\n\ni wonder if we marginise, can we generate seq-> structure -> seq. this is similiar trick for verification in language translation\n\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2F78d0cdd21371316f4b4121fccfb36cfb%2FSelection_999(8147).png?generation=1745797958749775&alt=media)\n\nhttps://x.com/zaixiang_zheng/status/1916311160842031433" }, "source": "meta" }