Awesome Multimodal
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Yarin Gal — most-cited papers & profile · Multimodal
← authors
·
overview
Yarin Gal
35
papers ·
686
citations ·
55
h-index
Apple (Israel) · Apple (United Kingdom) · Science Oxford · Apple (United States)
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Concrete Dropout
2017 · 145 citations
Kernel Language Entropy: Fine-grained Uncertainty Quantification For Llms From Semantic Similarities
2024 · 127 citations
Learning Invariant Representations for Reinforcement Learning without Reconstruction
2020 · 97 citations
VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
2019 · 65 citations
Invariant Causal Prediction for Block MDPs
2020 · 37 citations
Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations
2020 · 18 citations
Generalizing from a few environments in safety-critical reinforcement learning
2019 · 9 citations
Differentially Private Continual Learning
2019 · 6 citations
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
2021 · 5 citations
Adversarial recovery of agent rewards from latent spaces of the limit order book
2019 · 3 citations
Outcome-Driven Reinforcement Learning via Variational Inference
2021 · 3 citations
On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
2020 · 2 citations
On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations
2022 · 2 citations
ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
2023 · 2 citations
BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
2025 · 1 citations
Topics
Exploration
Safety & Alignment
Offline RL
Value-Based
Evaluation
cs.LG
stat.ML
Model-Based RL
Safe RL
Meta-RL