← Authors

Katja Hofmann

30 papers · 2009–2025 · 13 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (13) πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (16) 🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (6) πŸ—ΊοΈ Taxonomy Completionist (53) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸ† Keyword Champion (2) πŸ† Grand Slam πŸ—ƒοΈ Keyword Collector (105) ⚑ Prolific Year (5) πŸ“ˆ Trend Setter πŸ’Ž Century Club (30) πŸ”₯ Unstoppable (8) ❓ The Questioner

Conferences

NIPS (7) ICML (6) ICLR (4) IJCAI (3) AISTATS (2) AAAI (1) COLT (1) CONLL (1) CORL (1) EACL (1) ICCV (1) JMLR (1) UAI (1)

Top co-authors

Sam Devlin (8) Sebastian Tschiatschek (5) Shimon Whiteson (5) Pierre-yves Oudeyer (4) Luisa Zintgraf (4) Kamil Ciosek (4) Raluca Georgescu (4) Maximilian Igl (4) John Bronskill (3) RΓ©my Portelas (3)

Keywords

sample efficiency (5) reinforcement learning (3) task adaptation (3) deep reinforcement learning (3) few-shot learning (3) optimistic exploration (2) automatic curriculum learning (2) regret bound (2) temporal difference learning (2) dueling bandit (2) preference learning (2) sparse reward (2) domain generalization (1) imitation learning (1) approximate inference (1) online learning (1) image classification (1) neural network architecture (1) offline reinforcement learning (1) curriculum learning (1)

Papers

Scaling Laws for Pre-training Agents and World Models ICML 2025
Learning Safety Constraints from Demonstrations with Unknown Rewards AISTATS 2024
Imitating Human Behaviour with Diffusion Models ICLR 2023
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification NIPS 2022
Interactively Learning Preference Constraints in Linear Bandits ICML 2022
Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency AAAI 2022
Uni[MASK]: Unified Inference in Sequential Decision Problems NIPS 2022
Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation ICML 2021
ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition ICCV 2021
VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning JMLR 2021
Grounding Spatio-Temporal Language with Transformers NIPS 2021
Memory Efficient Meta-Learning with Large Images NIPS 2021
Strategically efficient exploration in competitive multi-agent reinforcement learning UAI 2021
Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning ICML 2021
TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL ICML 2021
Conservative Uncertainty Estimation By Fitting Prior Networks ICLR 2020
Variational Integrator Networks for Physically Structured Embeddings AISTATS 2020
VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning ICLR 2020
AMRL: Aggregated Memory For Reinforcement Learning ICLR 2020
Automatic Curriculum Learning For Deep RL: A Short Survey IJCAI 2020
Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning NIPS 2019
Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments CORL 2019
Better Exploration with Optimistic Actor Critic NIPS 2019
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck NIPS 2019
Fast Context Adaptation via Meta-Learning ICML 2019
Advancements in Dueling Bandits IJCAI 2018
The Malmo Platform for Artificial Intelligence Experimentation IJCAI 2016
Contextual Dueling Bandits COLT 2015
Generating a Non-English Subjectivity Lexicon: Relations That Matter EACL 2009
Lexical Patterns or Dependency Patterns: Which Is Better for Hypernym Extraction? CONLL 2009