David Lindner
10 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (4) 🗺️ Taxonomy Completionist (21) 🌍 Conference Polyglot (5)
🐣
Hot Topic Early Bird
💎
Century Club
(10)
🔥
Unstoppable
(5)
Conferences
NIPS (4)
ICLR (2)
ICML (2)
AISTATS (1)
IJCAI (1)
Top co-authors
Keywords
sample complexity
(2)
inverse reinforcement learning
(2)
online learning
(1)
preference learning
(1)
constrained reinforcement learning
(1)
model evaluation
(1)
model architecture
(1)
constrained markov decision process
(1)
model analysis
(1)
ai safety
(1)
convex optimization
(1)
bayesian model
(1)
reward function
(1)
reward learning
(1)
sample efficiency
(1)
multi-armed bandit
(1)
information gain
(1)
linear bandit
(1)
safety constraint
(1)
active learning
(1)
Papers
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
ICML 2025
On scalable oversight with weak LLMs judging strong LLMs
NIPS 2024
Learning Safety Constraints from Demonstrations with Unknown Rewards
AISTATS 2024
Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
ICLR 2024
Tracr: Compiled Transformers as a Laboratory for Interpretability
NIPS 2023
Active Exploration for Inverse Reinforcement Learning
NIPS 2022
Interactively Learning Preference Constraints in Linear Bandits
ICML 2022
Addressing the Long-term Impact of ML Decisions via Policy Regret
IJCAI 2021
Learning What To Do by Simulating the Past
ICLR 2021
Information Directed Reward Learning for Reinforcement Learning
NIPS 2021