Beyond Atoms: Enhancing Molecular Pretrained Representations with 3D Space Modeling
Summary of Lu et al.'s 2025 paper introducing SpaceFormer, a Transformer-based framework that models the entire 3D space around a molecule—not just …
Transformers
4 posts tagged with transformers.
Deconstructing recurrence, attention, and gating: Investigating the transferability of transformers and gated recurrent neural networks in forecasting of dynamical systems
Ablation study examining key architectural components of neural networks for spatiotemporal forecasting, finding that neural gating and attention …
Sarcasm Detection with Transformers: When Perfect Accuracy Isn't Perfect
Learn how dataset bias can lead to misleading results in NLP: a sarcasm detection model that actually learned to classify news sources.
CoQA Dataset: Advancing Conversational Question Answering
Explore CoQA: the conversational QA dataset that challenges AI with multi-turn dialogue, coreference resolution, and natural answers.