1
Perceiver: General Perception with Iterative Attention
Source ↗Andrew Jaegle, Felix Gimeno, Andrew Brock, Oriol Vinyals, Andrew Zisserman, Joao Carreira
Mar 4, 2021·495 checkouts·arxiv.org
Best Cs.lg Papers
The highest-signal papers on Cs.lg, ranked by community reviews and momentum.
Canonical intent: topic=cs-lg|type=paper|year=evergreen
Top Picks
2
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
Source ↗Ryan Lowe, Yi Wu, Aviv Tamar, Jean Harb, Pieter Abbeel, Igor Mordatch
Jun 7, 2017·495 checkouts·arxiv.org
3
Verifiable Intent: Cryptographic Anchoring for Autonomous Agency
Source ↗J. L. Martinez, Sarah Chen, Arjun Nair
Feb 20, 2026·494 checkouts·arxiv.org
4
Matching Networks for One Shot Learning
Source ↗Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, Daan Wierstra
Jun 13, 2016·471 checkouts·arxiv.org
5
Asymmetric self-play for automatic goal discovery in robotic manipulation
Source ↗OpenAI Robotics Team
Jan 14, 2021·470 checkouts·arxiv.org
6
Evaluating Large Language Models Trained on Code
Source ↗Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Wojciech Zaremba, Ilya Sutskever, et al.
Jul 7, 2021·459 checkouts·arxiv.org
7
Fast KV Compaction via Attention Matching
Source ↗Adam Zweiger, Xinghong Fu, Han Guo, MIT Team
Feb 18, 2026·454 checkouts·arxiv.org
8
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Source ↗Andrew Brock, Jeff Donahue, Karen Simonyan
Sep 28, 2018·448 checkouts·arxiv.org
9
Deep reinforcement learning from human preferences
Source ↗Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, Dario Amodei
Jun 12, 2017·436 checkouts·arxiv.org
10
Scaling Laws for Neural Language Models
Source ↗Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, Dario Amodei
Jan 23, 2020·433 checkouts·arxiv.org
11
Faster sorting algorithms discovered using deep reinforcement learning
Source ↗Daniel J. Mankowitz, Andrea Michi, Anton Zhernov, Marco Gelpi, Marco Selvi, Alhussein Fawzi
Jun 7, 2023·430 checkouts·doi.org
12
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
Source ↗Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican, Jordan Hoffmann, Francis Song, John Aslanides, Sarah Henderson, Roman Ring, Susannah Young, Eliza Rutherford, Tom Hennigan, Jacob Menick, Albin Cassirer, Richard Powell, George van den Driessche, Lisa Anne Hendricks, Maribeth Rauh, Po-Sen Huang, Amelia Glaese, Johannes Welbl, Sumanth Dathathri, Saffron Huang, Jonathan Uesato, John Mellor, Irina Higgins, Antonia Creswell, Nat McAleese, Amy Wu, Eleni Elia, Danilo J. Rezende, Vinyals, Simonyan
Dec 8, 2021·430 checkouts·arxiv.org
13
Learning to summarize from human feedback
Source ↗Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, Paul Christiano
Sep 2, 2020·413 checkouts·arxiv.org
14
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Source ↗Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, Jeff Wu
Dec 14, 2023·411 checkouts·arxiv.org
15
Human-level performance in 3D multiplayer games with population-based reinforcement learning
Source ↗Max Jaderberg, Wojciech M. Czarnecki, Iain Dunning, Luke Marris, Guy Lever, Antonio Garcia Castaneda, Charles Beattie, Neil C. Rabinowitz, Ari S. Morcos, Avraham Ruderman, Nicolas Sonnerat, Tim Green, Louise Deason, Joel Z. Leibo, David Silver, Demis Hassabis, Koray Kavukcuoglu, Thore Graepel
May 31, 2019·409 checkouts·doi.org
16
Mastering Diverse Domains through World Models
Source ↗Danijar Hafner, Jurgis Pasukonis, Jimmy Ba, Timothy Lillicrap
Jan 10, 2023·397 checkouts·arxiv.org
17
Let's Verify Step by Step
Source ↗Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, Karl Cobbe
May 31, 2023·393 checkouts·arxiv.org
18
Learning Dexterous In-Hand Manipulation
Source ↗Marcin Andrychowicz, Bowen Baker, Maciek Chociej, Rafal Jozefowicz, Bob McGrew, Jakub Pachocki, Arthur Petron, Matthias Plappert, Glenn Powell, Alex Ray, Jonas Schneider, Szymon Sidor, Josh Tobin, Peter Welinder, Lilian Weng, Wojciech Zaremba
Jul 30, 2018·393 checkouts·arxiv.org
19
Discovering faster matrix multiplication algorithms with reinforcement learning
Source ↗Alhussein Fawzi, Matej Balog, Aja Huang, Thomas Hubert, Pushmeet Kohli
Oct 5, 2022·389 checkouts·doi.org
20
21
Solving Rubik's Cube with a Robot Hand
Source ↗Ilge Akkaya, Marcin Andrychowicz, Maciek Chociej, Mateusz Litwin, Bob McGrew, Arthur Petron, Alex Paino, Matthias Plappert, Glenn Powell, Raphael Ribas, Jonas Schneider, Nikolas Tezak, Peter Welinder, Lilian Weng, Wojciech Zaremba, Lei Zhang
Oct 15, 2019·379 checkouts·arxiv.org
22
Emergent Tool Use From Multi-Agent Autocurricula
Source ↗Bowen Baker, Ingmar Kanitscheider, Todor Markov, Yi Wu, Glenn Powell, Bob McGrew, Igor Mordatch
Sep 17, 2019·378 checkouts·arxiv.org
23
Human-level control through deep reinforcement learning
Source ↗Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Demis Hassabis
Feb 26, 2015·355 checkouts·doi.org
24
KLong: Training LLM Agents for Extremely Long-horizon Tasks
Source ↗Yue Liu, Zhiyuan Hu, Flood Sung
Feb 19, 2026·352 checkouts·arxiv.org
25
Stateful Memory Compaction for Mitigating Context Rot in Long-Horizon Agents
Source ↗Zhixuan Fang, Yisong Yue, Anima Anandkumar
Feb 21, 2026·350 checkouts·arxiv.org
26
Scaling Laws for Autoregressive Generative Modeling
Source ↗Tom Henighan, Jared Kaplan, Mor Katz, Mark Chen, Christopher Hesse, Jacob Jackson, Heewoo Jun, Tom B. Brown, Prafulla Dhariwal, Scott Gray, Chris Hallacy, Benjamin Mann, Alec Radford, Aditya Ramesh, Nick Ryder, Daniel M. Ziegler, John Schulman, Dario Amodei, Sam McCandlish
Oct 28, 2020·345 checkouts·arxiv.org
27
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Source ↗Lasse Espeholt, Hubert Soyer, Remi Munos, Karen Simonyan, Volodymyr Mnih, Tom Ward, Yotam Doron, Vlad Firoiu, Tim Harley, Iain Dunning, Shane Legg, Koray Kavukcuoglu
Feb 9, 2018·344 checkouts·arxiv.org
28
Neural Discrete Representation Learning
Source ↗Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu
Nov 2, 2017·340 checkouts·arxiv.org
29
Learning skillful medium-range global weather forecasting
Source ↗Remi Lam, Alvaro Sanchez-Gonzalez, Matthew Willson, Peter Wirnsberger, Meire Fortunato, Alexander Alet, Suman Ravuri, Timo Ewalds, Zachary Eaton-Rosen, Weihua Hu, Alexander Merose, Stephan Hoyer, George Holland, Jacklynn Stott, Oriol Vinyals, Shakir Mohamed, Peter Battaglia
Nov 14, 2023·338 checkouts·doi.org
30
A Generalist Agent
Source ↗Scott Reed, Konrad Zolna, Emilio Parisotto, Sergio Gomez Colmenarejo, Nando de Freitas
May 12, 2022·325 checkouts·arxiv.org
FAQ
How is this “best Cs.lg Papers” collection ranked?
This page ranks Cs.lg Papers using topic relevance, checkout momentum, source diversity, and freshness signals. Rankings are recalculated as new items and engagement arrive, so readers see resources that are both high quality and currently useful for implementation, research, and practical decision making. Canonical intent key: topic=cs-lg|type=paper|year=evergreen.
How do you prevent duplicate collection pages?
Attendemia maps each slug variant, including best-of and year forms, to one canonical intent key. If two URLs describe the same topic, type, and timeframe, non-canonical versions permanently redirect. This consolidates crawl signals, avoids duplicate content dilution, and helps search engines index the strongest single page.
When does a year page stay separate from evergreen?
A year-specific page stays separate only when its item set is materially different from evergreen and has enough ranking depth. When overlap is high, the year URL redirects to the evergreen canonical page. This avoids thin duplication while preserving genuinely distinct annual collections for search users.
Are these paid recommendations?
No. These recommendations are not paid placements. Attendemia ranks items from public metadata, source quality coverage, and user engagement signals, then orders them by practical usefulness. Sponsorship does not buy rank position, so this page should be interpreted as editorial curation rather than advertising inventory.