FH
Felix Hill
cs.LGcs.AIcs.CLcs.CVstat.MLArtificial Intelligencecs.NEcs.ROLanguageartificial intelligence
On Valency
published · living versionsW_h5g9ucen·v1 · currentpublished
The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
with Antoine Bordes, Sumit Chopra, Jason Weston
1 version
Preprints & journals
59 papers in the corpus · 2014–2025SIMA 2: A Generalist Embodied Agent for Virtual Worlds2512.04797v1 · SIMA team: Adrian Bolton, Alexander Lerchner, Alexandra Cordell et al.2025 · 0 citationsarXiv
Scaling Instructable Agents Across Many Simulated Worlds2404.10179v3 · SIMA Team, Maria Abi Raad, Arun Ahuja et al.2024 · 9 citationsarXiv
Why transformers are obviously good models of language2408.03855v1 · Felix Hill2024 · 0 citationsarXiv
Language models show human-like content effects on reasoning tasks2207.07051v4 · Ishita Dasgupta, Andrew K. Lampinen, Stephanie C. Y. Chan et al.2022 · 53 citationsarXiv
Language models, like humans, show content effects on reasoning tasks.39015546 · Lampinen, Andrew K, Dasgupta, Ishita, Chan, Stephanie C Y et al.2024 · 66 citationsPNAS nexus. 2024;3(7):pgae233
LGBTQIA+ Cultural Competence in Physical Therapy: An Exploratory Qualitative Study From the Clinician's Perspective.38302087 · Hofmann, Melissa C, Mulligan, Nancy F, Bell, Karla A et al.2024 · 7 citationsPhysical therapy. 2024;104(4)
What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation2404.07129v1 · Aaditya K. Singh, Ted Moskovitz, Felix Hill et al.2024 · 2 citationsarXiv
SemPPL: Predicting pseudo-labels for better contrastive representations2301.05158v2 · Matko Bosnjak, Pierre H. Richemond, Nenad Tomasev et al.2023 · 4 citationsarXiv
The Transient Nature of Emergent In-Context Learning in Transformers2311.08360v3 · Aaditya K. Singh, Stephanie C.Y. Chan, Ted Moskovitz et al.2023 · 4 citationsarXiv
SODA: Bottleneck Diffusion Models for Representation Learning2311.17901v1 · Drew A. Hudson, Daniel Zoran, Mateusz Malinowski et al.2023 · 21 citationsarXiv
Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning2112.08369v3 · Wilka Carvalho, Andrew Lampinen, Kyriacos Nikiforou et al.2021 · 1 citationarXiv
Know your audience: specializing grounded language models with listener subtraction2206.08349v2 · Aaditya K. Singh, David Ding, Andrew Saxe et al.2022 · 2 citationsarXiv
Semantic Exploration from Language Abstractions and Pretrained Representations2204.05080v3 · Allison C. Tam, Neil C. Rabinowitz, Andrew K. Lampinen et al.2022 · 20 citationsarXiv
Vision-Language Models as Success Detectors2303.07280v1 · Yuqing Du, Ksenia Konyushkova, Misha Denil et al.2023 · 11 citationsarXiv
The Edge of Orthogonality: A Simple View of What Makes BYOL Tick2302.04817v1 · Pierre H. Richemond, Allison Tam, Yunhao Tang et al.2023 · 1 citationarXiv
Collaborating with language models for embodied reasoning2302.00763v1 · Ishita Dasgupta, Christine Kaeser-Chen, Kenneth Marino et al.2023 · 9 citationsarXiv
Data Distributional Properties Drive Emergent In-Context Learning in Transformers2205.05055v6 · Stephanie C.Y. Chan, Adam Santoro, Andrew K. Lampinen et al.2022 · 61 citationsarXiv
Transformers generalize differently from information stored in context vs in weights2210.05675v2 · Stephanie C.Y. Chan, Ishita Dasgupta, Junkyung Kim et al.2022 · 11 citationsarXiv
Can language models learn from explanations in context?2204.02329v4 · Andrew K. Lampinen, Ishita Dasgupta, Stephanie C. Y. Chan et al.2022 · 160 citationsarXiv
Meaning without reference in large language models2208.02957v2 · Steven T. Piantadosi, Felix Hill2022 · 72 citationsarXiv
Zipfian environments for Reinforcement Learning2203.08222v2 · Stephanie C. Y. Chan, Andrew K. Lampinen, Pierre H. Richemond et al.2022 · 3 citationsarXiv
Tell me why! Explanations support learning relational and causal structure2112.03753v3 · Andrew K. Lampinen, Nicholas A. Roy, Ishita Dasgupta et al.2021 · 9 citationsarXiv
Publishing fast and slow: A path toward generalizability in psychology and AI.35139966 · Lampinen, Andrew K, Chan, Stephanie C Y, Santoro, Adam et al.2022 · 5 citationsThe Behavioral and brain sciences. 2022;45:e26
Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning2112.03763v2 · DeepMind Interactive Agents Team: Josh Abramson, Arun Ahuja, Arthur Brussee et al.2021 · 33 citationsarXiv
Towards mental time travel: a hierarchical memory for reinforcement learning agents2105.14039v3 · Andrew Kyle Lampinen, Stephanie C.Y. Chan, Andrea Banino et al.2021 · 13 citationsAdvances in Neural Information Processing Systems, 2021
Attention over learned object embeddings enables complex visual reasoning2012.08508v3 · David Ding, Felix Hill, Adam Santoro et al.2020 · 17 citationsarXiv
BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation2110.09147v1 · Thomas Scialom, Felix Hill2021 · 3 citationsarXiv
Multimodal Few-Shot Learning with Frozen Language Models2106.13884v2 · Maria Tsimpoukelli, Jacob Menick, Serkan Cabi et al.2021 · 86 citationsarXiv
Publishing fast and slow: A path toward generalizability in psychology and AIy4az2_v1 · Andrew Kyle Lampinen, Stephanie C. Y. Chan, Adam Santoro et al.2021 · 4 citationsPsyArXiv
Imitating Interactive Intelligence2012.05672v2 · Josh Abramson, Arun Ahuja, Iain Barr et al.2020 · 42 citationsarXiv
Placing language in an integrated understanding system: Next steps toward human-level performance in neural language models.32989131 · McClelland, James L, Hill, Felix, Rudolph, Maja et al.2020 · 94 citationsProceedings of the National Academy of Sciences of the United States of America. 2020;117(42):25966-25974
Grounded Language Learning Fast and Slow2009.01719v4 · Felix Hill, Olivier Tieleman, Tamara von Glehn et al.2020 · 38 citationsarXiv
Extending Machine Language Models toward Human-Level Language Understanding1912.05877v2 · James L. McClelland, Felix Hill, Maja Rudolph et al.2019 · 0 citationsarXiv
Probing Emergent Semantics in Predictive Agents via Question Answering2006.01016v1 · Abhishek Das, Federico Carnevale, Hamza Merzic et al.2020 · 5 citationsarXiv
Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text2005.09382v1 · Felix Hill, Sona Mokra, Nathaniel Wong et al.2020 · 32 citationsarXiv
Applying machine learning optimization methods to the production of a quantum gas1908.08495v2 · Adam J. Barker, Harry Style, Kathrin Luksch et al.2019 · 37 citationsMach. Learn.: Sci. Technol. 1 015007 (2020)
Environmental drivers of systematicity and generalization in a situated agent1910.00571v4 · Felix Hill, Andrew Lampinen, Rosalia Schneider et al.2019 · 85 citationsarXiv
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems1905.00537v3 · Alex Wang, Yada Pruksachatkun, Nikita Nangia et al.2019 · 1,346 citationsarXiv
Learning to Understand Goal Specifications by Modelling Reward1806.01946v4 · Dzmitry Bahdanau, Felix Hill, Jan Leike et al.2018 · 62 citationsarXiv
Is coding a relevant metaphor for building AI?31775918 · Santoro, Adam, Hill, Felix, Barrett, David et al.2019 · 3 citationsThe Behavioral and brain sciences. 2019;42:e240
Understanding Early Word Learning in Situated Artificial Agents1710.09867v2 · Felix Hill, Stephen Clark, Karl Moritz Hermann et al.2017 · 22 citationsarXiv
Higher-order Comparisons of Sentence Encoder Representations1909.00303v2 · Mostafa Abdou, Artur Kulmizev, Felix Hill et al.2019 · 16 citationsarXiv
Is coding a relevant metaphor for building AI? A commentary on "Is coding a relevant metaphor for the brain?", by Romain Brette1904.10396v1 · Adam Santoro, Felix Hill, David Barrett et al.2019 · 0 citationsarXiv
Analysing Mathematical Reasoning Abilities of Neural Models1904.01557v1 · David Saxton, Edward Grefenstette, Felix Hill et al.2019 · 85 citationsarXiv
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding1804.07461v3 · Alex Wang, Amanpreet Singh, Julian Michael et al.2018 · 5,683 citationsarXiv
Learning to Make Analogies by Contrasting Abstract Relational Structure1902.00120v1 · Felix Hill, Adam Santoro, David G.T. Barrett et al.2019 · 58 citationsarXiv
Generating Diverse Programs with Instruction Conditioned Reinforced Adversarial Learning1812.00898v1 · Aishwarya Agrawal, Mateusz Malinowski, Felix Hill et al.2018 · 1 citationarXiv
Neural Arithmetic Logic Units1808.00508v1 · Andrew Trask, Felix Hill, Scott Reed et al.2018 · 77 citationsarXiv
Measuring abstract reasoning in neural networks1807.04225v1 · David G.T. Barrett, Felix Hill, Adam Santoro et al.2018 · 141 citationsarXiv
Grounded Language Learning in a Simulated 3D World1706.06551v2 · Karl Moritz Hermann, Felix Hill, Simon Green et al.2017 · 147 citationsarXiv
Career total: 93 works. 59 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.