🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Designing BERT for convolutional networks: sparse and hierarchical masked modeling Keyu Tian, Yi Jiang, Qishuai Diao, Chen Lin, Liwei Wang, Zehuan Yuan tl;dr: create image, which looks to CNN same, as transformers -> MIM starts working arxiv.org/abs/2301.03580…

The paper designs a working MLM style pretraining for convnets! Huge if this really works.

How can we leverage successful pretraining techniques from transformers to improve purely convolutional networks? The answer is *Sparse Convolutions*! Let's see what happens when purely convolutional networks are pretrained with 1.28 million unlabeled images ... 1/7

Are RGB inputs good enough for open-world generalization of object detection? Excited to share our #ICLR2023 paper GOOD -- we show that geometric cues can significantly boost the performance for the task! arxiv.org/abs/2212.11720 (Joint work with @AutoVisionGroup Dan Zhang )

New preprint! 🚨 We scale equilibrium sampling to hexapeptide (in cartesian coordinates!) with Sequential Boltzmann generators!  📈 🤯 Work with Joey Bose, Chen Lin, Leon Klein, Michael Bronstein and Alex Tong Thread 🧵 1/11

New work with Lars Schaaf, Chen Lin, Guangrun Wang, and philip: We optimize neural networks to smoothly represent minimum energy paths and predict transition states for chemical reactions. Compared to the traditional approach, our method shows (i) improved resilience to