SO
Simon Osindero
cs.LGcs.AIstat.MLcs.CVcs.NEcs.CLcs.CYNeural Networks, ComputerAlgorithmscs.LO
On Valency
published · living versionsW_n9ub7d6b·v1 · currentpublished
Preprints & journals
61 papers in the corpus · 2006–2026KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs2609.39588v1 · Aravindh Mahendran, Michael King, Matthew Koichi Grimes et al.2026 · 0 citationsECCV 2026, 2026, pages 194--212
Agentic Economies for Autonomous Scientific Discovery2609.31562v1 · Nenad Tomasev, Matija Franklin, Atoosa Kasirzadeh et al.2026 · 0 citationsarXiv
AI Value Alignment for Evolving Social Norms2607.18506v1 · Nenad Tomasev, Matija Franklin, Simon Osindero2026 · 0 citationsarXiv
MaD Physics: Evaluating information seeking under constraints in physical environments2605.10820v1 · Moksh Jain, Mehdi Bennani, Johannes Bausch et al.2026 · 0 citationsarXiv
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals2604.22271v2 · Dharshan Kumaran, Viorica Patraucean, Simon Osindero et al.2026 · 0 citationsarXiv
Causal Evidence that Language Models use Confidence to Drive Behavior2603.22161v3 · Dharshan Kumaran, Nathaniel Daw, Simon Osindero et al.2026 · 0 citationsarXiv
How do LLMs Compute Verbal Confidence2603.17839v4 · Dharshan Kumaran, Arthur Conmy, Federico Barbero et al.2026 · 0 citationsarXiv
A Theory of Appropriateness That Accounts for Norms of Rationality2603.14050v1 · Joel Z. Leibo, Alexander Sasha Vezhnevets, Manfred Diaz et al.2026 · 0 citationsarXiv
Intelligent AI Delegation2602.11865v1 · Nenad Tomasev, Matija Franklin, Simon Osindero2026 · 4 citationsarXiv
Perplexity Cannot Always Tell Right from Wrong2601.22950v1 · Petar Velickovi'c, Federico Barbero, Christos Perivolaropoulos et al.2026 · 0 citationsarXiv
Virtual Agent Economies2509.10147v1 · Nenad Tomasev, Matija Franklin, Joel Z. Leibo et al.2025 · 0 citationsarXiv
Multi-Actor Generative Artificial Intelligence as a Game Engine2507.08892v1 · Alexander Sasha Vezhnevets, Jayd Matyas, Logan Cross et al.2025 · 0 citationsarXiv
How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models2507.03120v1 · Dharshan Kumaran, Stephen M Fleming, Larisa Markeeva et al.2025 · 1 citationarXiv
Wanting to Be Understood Explains the Meta-Problem of Consciousness2506.12086v1 · Chrisantha Fernando, Dylan Banarse, Simon Osindero2025 · 0 citationsarXiv
Societal and technological progress as sewing an ever-growing, ever-changing, patchy, and polychrome quilt2505.05197v1 · Joel Z. Leibo, Alexander Sasha Vezhnevets, William A. Cunningham et al.2025 · 0 citationsarXiv
Wanting to be Understood2504.06611v2 · Chrisantha Fernando, Dylan Banarse, Simon Osindero2025 · 0 citationsarXiv
A theory of appropriateness with applications to generative artificial intelligence2412.19010v1 · Joel Z. Leibo, Alexander Sasha Vezhnevets, Manfred Diaz et al.2024 · 1 citationarXiv
TRecViT: A Recurrent Video Transformer2412.14294v2 · Viorica Patraucean, Xu Owen He, Joseph Heyward et al.2024 · 0 citationsarXiv
Neural Compression of Atmospheric States2407.11666v2 · Piotr Mirowski, David Warde-Farley, Mihaela Rosca et al.2024 · 0 citationsarXiv
Genie: Generative Interactive Environments2402.15391v1 · Jake Bruce, Michael Dennis, Ashley Edwards et al.2024 · 23 citationsarXiv
Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia2312.03664v2 · Alexander Sasha Vezhnevets, John P. Agapiou, Avia Aharon et al.2023 · 14 citationsarXiv
Solving MaxSAT with Matrix Multiplication2311.02101v1 · David Warde-Farley, Vinod Nair, Yujia Li et al.2023 · 0 citationsarXiv
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution2309.16797v1 · Chrisantha Fernando, Dylan Banarse, Henryk Michalewski et al.2023 · 31 citationsarXiv
Perception Test: A Diagnostic Benchmark for Multimodal Video Models2305.13786v2 · Viorica Patraucean, Lucas Smaira, Ankush Gupta et al.2023 · 34 citationsarXiv
CLIP-CLOP: CLIP-Guided Collage and Photomontage2205.03146v3 · Piotr Mirowski, Dylan Banarse, Mateusz Malinowski et al.2022 · 8 citationsarXiv
Training Compute-Optimal Large Language Models2203.15556v1 · Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch et al.2022 · 925 citationsarXiv
Retrieval-Augmented Reinforcement Learning2202.08417v4 · Anirudh Goyal, Abram L. Friesen, Andrea Banino et al.2022 · 23 citationsarXiv
Unified Scaling Laws for Routed Language Models2202.01169v2 · Aidan Clark, Diego de las Casas, Aurelia Guy et al.2022 · 40 citationsarXiv
Model-Value Inconsistency as a Signal for Epistemic Uncertainty2112.04153v3 · Angelos Filos, Eszter V'ertes, Zita Marinho et al.2021 · 1 citationarXiv
Improving language models by retrieving from trillions of tokens2112.04426v3 · Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann et al.2021 · 382 citationsarXiv
Scaling Language Models: Methods, Analysis & Insights from Training Gopher2112.11446v2 · Jack W. Rae, Sebastian Borgeaud, Trevor Cai et al.2021 · 234 citationsarXiv
Top-KAST: Top-K Always Sparse Training2106.03517v1 · Siddhant M. Jayakumar, Razvan Pascanu, Jack W. Rae et al.2021 · 38 citationsAdvances in Neural Information Processing Systems, 33, 20744-20754
Generative Art Using Neural Visual Grammars and Dual Encoders2105.00162v2 · Chrisantha Fernando, S. M. Ali Eslami, Jean-Baptiste Alayrac et al.2021 · 7 citationsarXiv
Contrastive Topographic Models: Energy-based density models applied to the understanding of sensory coding and cortical topography2011.03535v1 · Simon Osindero2020 · 0 citationsarXiv
From Language Games to Drawing Games2010.02820v2 · Chrisantha Fernando, Daria Zenkova, Stanislav Nikolov et al.2020 · 3 citationsarXiv
Small Data, Big Decisions: Model Selection in the Small-Data Regime2009.12583v1 · Jorg Bornschein, Francesco Visin, Simon Osindero2020 · 23 citationsProceedings of the International Conference on Machine (ICML 2020)
A Practical Sparse Approximation for Real Time Recurrent Learning2006.07232v1 · Jacob Menick, Erich Elsen, Utku Evci et al.2020 · 9 citationsarXiv
AlgebraNets2006.07360v2 · Jordan Hoffmann, Simon Schmitt, Simon Osindero et al.2020 · 2 citationsarXiv
A Deep Neural Network's Loss Surface Contains Every Low-dimensional Pattern1912.07559v2 · Wojciech Marian Czarnecki, Simon Osindero, Razvan Pascanu et al.2019 · 3 citationsarXiv
Adapting Behaviour for Learning Progress1912.06910v1 · Tom Schaul, Diana Borsa, David Ding et al.2019 · 10 citationsarXiv
Meta-Learning Deep Energy-Based Memory Models1910.02720v2 · Sergey Bartunov, Jack W Rae, Simon Osindero et al.2019 · 23 citationsarXiv
Meta-learning of Sequential Strategies1905.03030v2 · Pedro A. Ortega, Jane X. Wang, Mark Rowland et al.2019 · 47 citationsarXiv
Distilling Policy Distillation1902.02186v1 · Wojciech Marian Czarnecki, Razvan Pascanu, Simon Osindero et al.2019 · 72 citationsarXiv
Meta-Learning with Latent Embedding Optimization1807.05960v3 · Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski et al.2018 · 1,068 citationsarXiv
Massively Parallel Video Networks1806.03863v2 · Joao Carreira, Viorica Patraucean, Laurent Mazare et al.2018 · 2 citationsarXiv
Meta-Learning by the Baldwin Effect1806.07917v2 · Chrisantha Thomas Fernando, Jakub Sygnowski, Simon Osindero et al.2018 · 25 citationsarXiv
Mix&Match - Agent Curricula for Reinforcement Learning1806.01780v1 · Wojciech Marian Czarnecki, Siddhant M. Jayakumar, Max Jaderberg et al.2018 · 32 citationsarXiv
Kickstarting Deep Reinforcement Learning1803.03835v1 · Simon Schmitt, Jonathan J. Hudson, Augustin Zidek et al.2018 · 67 citationsarXiv
Population Based Training of Neural Networks1711.09846v2 · Max Jaderberg, Valentin Dalibard, Simon Osindero et al.2017 · 284 citationsarXiv
Beautiful and damned. Combined effect of content quality and social ties on user engagement1711.00536v1 · Luca M. Aiello, Rossano Schifanella, Miriam Redi et al.2017 · 11 citationsarXiv
Career total: 83 works. 61 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.