This page shows the most relevant public items for Machine Learning, ranked by trend activity and review signal. Use weekly for fast changes, monthly for more stable patterns, and all-time for evergreen picks.
Paper • Feb 13, 2026 • arXiv • Zijing Ou, Jacob Si, Junyi Zhu, Yingzhen Li
Diffusion alignment aims to optimize diffusion models for downstream objectives. While existing methods based on RL achieve success, they often suffer from reward over-optimization and mode collaps...
Paper • Feb 10, 2026 • bioRxiv • Eduardo da Veiga Beltrame
This paper presents a systematic benchmark of architectural hyperparameters for variational autoencoder (VAE) methods in single-cell RNA-seq batch integration. The study compares scVI, MrVI, and LD...
Paper • Feb 16, 2026 • bioRxiv • Anonymous Team
The paper introduces an automated deep learning tool for the real-time assessment of pain in mice using the Mouse Grimace Scale (MGS). The model was trained on a large and diverse dataset with non-...
Paper • Feb 23, 2026 • bioRxiv • Zhang, X., Jeong, E., Yan, C., Feng, Y., Lyu, L., Guo, X., Chen, Y.
CellAwareGNN is a new graph neural network (GNN) foundation model that integrates single-cell enhanced knowledge graphs for drug indication prediction. By modeling the complex relationships between...
Paper • Feb 1, 2026 • arXiv • Fan Chen, Sinho Chewi, Constantinos Daskalakis, Alexander Rakhlin
We present algorithms for diffusion model sampling which obtain δ-error in polylog(1/δ) steps, given access to eO(δ)-accurate score estimates in L2. This is an exponential improvement over all prev...
Paper • Feb 17, 2026 • arXiv • Moritz Miller, Florent Draye, Bernhard Schölkopf
This paper addresses the fundamental challenge of 'feature disentanglement' in modern deep learning. We propose an Orthogonality Regularization technique to identify features that are both interpre...
Blog • Feb 14, 2026 • Medium • Shane Collins
In 2026, ML has moved from the cloud to our pockets, handling the 'normal messiness' of real life. This post explores the small, invisible ways AI has cleaned up our lives, from transcripts that ha...
Other • Nov 23, 2015 • attendemia.com • Unknown Author
We introduce the "exponential linear unit" (ELU) which speeds up learning in deep neural networks and leads to higher classification accuracies. Like rectifi...
Paper • Feb 19, 2014 • arxiv.org • Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, Rob Fergus
Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succ...
Paper • Feb 19, 2015 • arxiv.org • Wojciech Zaremba, Ilya Sutskever, Oriol Vinyals
We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, ...
Paper • May 30, 2015 • arxiv.org • Minh-Thang Luong, Ilya Sutskever, Quoc V. Le, Oriol Vinyals, Wojciech Zaremba
Neural Machine Translation (NMT) is a new approach to machine translation that has shown promising results that are comparable to traditional approaches. A significant weakness in conventional NMT ...
Paper • Dec 11, 2014 • arxiv.org • Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, Yoshua Bengio
In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long s...
Paper • Jun 24, 2014 • arxiv.org • Volodymyr Mnih, Nicolas Heess, Alex Graves, Koray Kavukcuoglu
Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent n...
Paper • Jul 22, 2015 • arxiv.org • Oriol Vinyals, Quoc Le
Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., boo...
Paper • Nov 17, 2015 • arxiv.org • Andrej Karpathy, Justin Johnson, Li Fei-Fei
Recurrent Neural Networks (RNNs), and specifically a variant with Long Short-Term Memory (LSTM), are enjoying renewed interest as a result of successful applications in a wide range of machine lear...
Paper • Jun 22, 2015 • arxiv.org • Jason Yosinski, Jeff Clune, Anh Nguyen, Thomas Fuchs, Hod Lipson
Recent years have produced great advances in training large, deep neural networks (DNNs), including notable successes in training convolutional neural networks (convnets) to recognize natural image...
Paper • May 17, 2015 • arxiv.org • Hyeonwoo Noh, Seunghoon Hong, Bohyung Han
We propose a novel semantic segmentation algorithm by learning a deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution netw...
Paper • Dec 1, 2015 • arxiv.org • Yoon Kim, Yacine Jernite, David Sontag, Alexander M. Rush
We describe a simple neural language model that relies only on character-level inputs. Predictions are still made at the word-level. Our model employs a convolutional neural network (CNN) and a hig...
Paper • May 30, 2015 • arxiv.org • Kai Sheng Tai, Richard Socher, Christopher D. Manning
Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have...
Paper • Feb 15, 2016 • arxiv.org • Song Han, Huizi Mao, William J. Dally
Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources. To address this limitation, we introduc...