Skip to content
conftrace_

Simon Osindero

26 papers · 2003–2024 · 7 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+12 more ↓ πŸ—ΊοΈ Taxonomy Completionist (55) πŸƒ Academic Marathon Β· Ultra 🌍 Conference Polyglot Β· Silver πŸŒ‰ Interdisciplinary Bridge Β· Bronze 🐣 Hot Topic Early Bird
🌱 Topic Pioneer πŸ‘₯ Mega-Team Β· Squad πŸ† Keyword Champion 🧭 Keyword Pioneer πŸ‘‘ Triple Crown 🌟 Keyword Trendsetter Combo (7) ⚑ Prolific Year Β· Productive πŸ”₯ Unstoppable Β· Bronze πŸš€ Conference Pioneer πŸ’Ž Century Club Β· Bronze πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (130)

Venues

ICML (11) NeurIPS (7) ICLR (4) AISTATS (1) CVPR (1) ECCV (1) JMLR (1)

Top co-authors

Oriol Vinyals (7) Jack Rae (6) Razvan Pascanu (6) Max Jaderberg (6) Erich Elsen (5) Nicolas Heess (5) Koray Kavukcuoglu (5) Karen Simonyan (4) Laurent Sifre (3) Aurelia Guy (3)

Research topics

Machine Learning (17) Deep Learning (14) Artificial Intelligence (13) Reinforcement Learning (8) Core AI (8) Methods (8) Optimization & Theory (8) Core Methods (7) Learning Types Β· Deep Learning (6) Learning Types Β· Machine Learning (5) Models (5) Natural Language Processing (4) Application Areas (4) Techniques (4) Applications (3)

Keywords

neural network (3) recurrent neural network (3) model compression (2) large language model (2) reinforcement learning (2) attention mechanism (2) scaling law (2) knowledge distillation (2) few-shot learning (2) neural network architecture (2) energy-based model (2) synthetic gradient (2) deep reinforcement learning (2) temporal abstraction (2) independent component analysis (1) blind source separation (1) online learning (1) model selection (1) zero-shot learning (1) epistemic uncertainty (1)

Papers

Genie: Generative Interactive Environments ICML 2024 Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution ICML 2024 Perception Test: A Diagnostic Benchmark for Multimodal Video Models NeurIPS 2023 An empirical analysis of compute-optimal large language model training NeurIPS 2022 Improving Language Models by Retrieving from Trillions of Tokens ICML 2022 Model-Value Inconsistency as a Signal for Epistemic Uncertainty ICML 2022 Retrieval-Augmented Reinforcement Learning ICML 2022 Unified Scaling Laws for Routed Language Models ICML 2022 Entropic Desired Dynamics for Intrinsic Control NeurIPS 2021 Practical Real Time Recurrent Learning with a Sparse Approximation ICLR 2021 Meta-Learning Deep Energy-Based Memory Models ICLR 2020 Multiplicative Interactions and Where to Find Them ICLR 2020 Small Data, Big Decisions: Model Selection in the Small-Data Regime ICML 2020 Top-KAST: Top-K Always Sparse Training NeurIPS 2020 Distilling Policy Distillation AISTATS 2019 Meta-Learning with Latent Embedding Optimization ICLR 2019 Massively Parallel Video Networks ECCV 2018 Mix & Match Agent Curricula for Reinforcement Learning ICML 2018 Decoupled Neural Interfaces using Synthetic Gradients ICML 2017 FeUdal Networks for Hierarchical Reinforcement Learning ICML 2017 Sobolev Training for Neural Networks NeurIPS 2017 Understanding Synthetic Gradients and Decoupled Neural Interfaces ICML 2017 Recursive Recurrent Nets With Attention Modeling for OCR in the Wild CVPR 2016 Strategic Attentive Writer for Learning Macro-Actions NeurIPS 2016 Modeling image patches with a directed hierarchy of Markov random fields NeurIPS 2007 Energy-Based Models for Sparse Overcomplete Representations JMLR 2003