EloRater: Best AI Research Paper?
Submit your groundbreaking AI research paper for a chance to be recognized as the best in the field. Papers will be judged on innovation, impact, and clarity.
Total Votes: 41
Time Left:
| Rank | Elo Rating | Paper Title | Abstract | Author | Link | Actions |
|---|---|---|---|---|---|---|
| 1 | 1100 | Attention Is All You Need | This paper introduces the Transformer, a novel neural network architecture abandoning recurrence anā¦ | Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Åukasz Kaiā¦ | Link | |
| 2 | 1058 | ImageNet Classification with Deep Convolutional Neural Networks | This paper presents a large, deep convolutional neural network (CNN) that achieved groundbreaking rā¦ | Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton | Link | |
| 3 | 1046 | Variational Lossy Autoencoder | This paper introduces the Variational Lossy Autoencoder (VLAE), a generative model combining Variatā¦ | Xi Chen, Diederik P. Kingma, Tim Salimans, Yan Duan, Prafulla Dhariwal, John Schulman, Ilya Sutskevā¦ | Link | |
| 4 | 1031 | The Unreasonable Effectiveness of Recurrent Neural Networks | This article highlights the surprising power and simplicity of Recurrent Neural Networks (RNNs). Itā¦ | Andrej Karpathy | Link | |
| 5 | 1029 | A Simple Neural Network Module for Relational Reasoning | This paper introduces Relation Networks (RNs), a simple, plug-and-play neural network module designā¦ | Adam Santoro, David Raposo, David G.T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter Battagliaā¦ | Link | |
| 6 | 1017 | The First Law of Complexodynamics | This article explores Sean Carroll's question about why complexity in physical systems seems to risā¦ | Scott Aaronson | Link | |
| 7 | 1016 | Keeping Neural Networks Simple by Minimizing the Description Length of the Weights | This paper proposes a neural network regularization method based on the Minimum Description Length ā¦ | Geoffrey E. Hinton, Drew van Camp | Link | |
| 8 | 1015 | Variational Lossy Autoencoder | This paper introduces the Variational Lossy Autoencoder (VLAE), a generative model combining Variatā¦ | Xi Chen, Diederik P. Kingma, Tim Salimans, Yan Duan, Prafulla Dhariwal, John Schulman, Ilya Sutskevā¦ | Link | |
| 9 | 1001 | Relational Recurrent Neural Networks | This paper addresses the limitations of standard recurrent architectures like LSTMs in tasks demandā¦ | Adam Santoro, Ryan Faulkner, David Raposo, Jack Rae, Mike Chrzanowski, ThĆ©ophane Weber, Daan Wierstā¦ | Link | |
| 10 | 1000 | Generative Ghosts: Anticipating Benefits and Risks of AI Afterlives | As AI systems quickly improve in both breadth and depth of performance, they lend themselves to creā¦ | Meredith Ringel Morris and Jed R. Brubaker | Link | |
| 11 | 1000 | Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA | Large language models (LLMs) are computationally expensive to deploy. Parameter sharing offers a prā¦ | Sangmin Bae, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Seungyeon Kim, Tal Schuster | Link | |
| 12 | 1000 | Massively Scalable Inverse Reinforcement Learning for Route Optimization | Globally-scalable route optimization based on human preferences remains an open problem. Although pā¦ | Matt Barnes, Matthew Abueg, Oliver F. Lange, Matt Deeds, Jason Trader, Denali Molitor, Markus Wulfmā¦ | Link | |
| 13 | 1000 | Mamba: Linear-Time Sequence Modeling with Selective State Spaces | Foundation models, now powering most of the exciting applications in deep learning, are almost univā¦ | Albert Gu, Tri Dao | Link | |
| 14 | 1000 | DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning | We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zā¦ | DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, ā¦ | Link | |
| 15 | 1000 | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | We introduce a new language representation model called BERT, which stands for Bidirectional Encodeā¦ | Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova | Link | |
| 16 | 1000 | Bridging Algorithmic Information Theory and Machine Learning, Part II: Clustering, Density Estimatiā¦ | Machine Learning (ML) and Algorithmic Information Theory (AIT) offer distinct yet complementary appā¦ | Marcus Hutter | Link | |
| 17 | 1000 | MELODI: Exploring Memory Compression for Long Contexts Published | We present MELODI, a novel memory architecture designed to efficiently process long documents usingā¦ | Yinpeng Chen, DeLesley Hutchins, Aren Jansen, Andrey Zhmoginov, David Racz, Jesper Andersen | Link | |
| 18 | 1000 | Generative Ghosts: Anticipating Benefits and Risks of AI Afterlives | As AI systems quickly improve in both breadth and depth of performance, they lend themselves to creā¦ | Meredith Ringel Morris and Jed R. Brubaker | Link | |
| 19 | 1000 | Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty | User prompts for generative AI models are often underspecified, leading to sub-optimal responses. Tā¦ | Meera Hahn, Wenjun Zeng, Nithish Kannen, Rich Galt, Kartikeya Badola, Been Kim, Zi Wang | Link | |
| 20 | 1000 | Generative Ghosts: Anticipating Benefits and Risks of AI Afterlives | As AI systems quickly improve in both breadth and depth of performance, they lend themselves to creā¦ | Meredith Ringel Morris and Jed R. Brubaker | Link | |
| 21 | 1000 | Flow-Lenia: Emergent evolutionary dynamics in mass conservative continuous cellular automata Publiā¦ | Central to the artificial life endeavour is the creation of artificial systems spontaneously generaā¦ | Erwan Plantec, Gautier Hamon, Mayalen Etcheverry, Bert Wang-Chak Chan, Pierre-Yves Oudeyer, ClĆ©mentā¦ | Link | |
| 22 | 1000 | Accurate Structure Prediction of Biomolecular Interactions with AlphaFold 3 | The introduction of AlphaFoldā21 has spurred a revolution in modelling the structure of proteins anā¦ | Josh Abramson, Jonas Adler, Jack Dunger, Richard Evans, Tim Green, Alexander Pritzel, Olaf Ronneberā¦ | Link | |
| 23 | 1000 | Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA | Large language models (LLMs) are computationally expensive to deploy. Parameter sharing offers a prā¦ | Sangmin Bae, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Seungyeon Kim, Tal Schuster | Link | |
| 24 | 998 | Multi-Scale Context Aggregation by Dilated Convolutions | This paper introduces dilated convolutions (also known as atrous convolutions) as a method to aggreā¦ | Fisher Yu, Vladlen Koltun | Link | |
| 25 | 988 | Understanding LSTM Networks | This article explains Long Short-Term Memory (LSTM) networks, a type of Recurrent Neural Network (Rā¦ | Christopher Olah | Link | |
| 26 | 986 | Deep Residual Learning for Image Recognition | This paper introduces Deep Residual Networks (ResNets), an architecture designed to ease the trainiā¦ | Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun | Link | |
| 27 | 985 | Identity Mappings in Deep Residual Networks | This paper analyzes the critical role of identity mappings within the shortcut connections of Deep ā¦ | Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun | Link | |
| 28 | 971 | Neural Machine Translation by Jointly Learning to Align and Translate | This paper addresses limitations in traditional neural machine translation (NMT) encoder-decoder moā¦ | Dzmitry Bahdanau, KyungHyun Cho, Yoshua Bengio | Link | |
| 29 | 970 | Order Matters: Sequence to Sequence for Sets | This paper investigates the impact of input and output element order on sequence-to-sequence (seq2sā¦ | Oriol Vinyals, Samy Bengio, Manjunath Kudlur | Link | |
| 30 | 968 | GPipe: Easy Scaling with Micro-Batch Pipeline Parallelism | This paper introduces GPipe, a library facilitating the training of extremely large neural networksā¦ | Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Mia Xu Chen, Dehao Chen, HyoukJoong Lee, Jiā¦ | Link | |
| 31 | 954 | Neural Turing Machines | This paper introduces Neural Turing Machines (NTMs), a neural network architecture augmented with aā¦ | Alex Graves, Greg Wayne, Ivo Danihelka | Link | |
| 32 | 941 | Pointer Networks | This paper introduces Pointer Networks (Ptr-Nets), a neural architecture designed to address the liā¦ | Oriol Vinyals, Meire Fortunato, Navdeep Jaitly | Link | |
| 33 | 926 | Neural Message Passing for Quantum Chemistry | This paper introduces Message Passing Neural Networks (MPNNs) as a framework for predicting quantumā¦ | Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, George E. Dahl | Link |