János Kramár
9 papers · 2010–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) 🏃 Academic Marathon (14)
🐝
Cross-Pollinator
(4)
🌈
Renaissance Researcher
(5)
🗺️
Taxonomy Completionist
(21)
Conferences
NIPS (4)
ACL (1)
EMNLP (1)
ICLR (1)
IJCAI (1)
RSS (1)
Top co-authors
Keywords
deep reinforcement learning
(2)
neural network
(2)
sparse autoencoder
(2)
model analysis
(2)
multi-agent system
(2)
robotic manipulation
(1)
sim-to-real transfer
(1)
zero-shot learning
(1)
neural network interpretability
(1)
imitation learning
(1)
ai safety
(1)
continuous optimization
(1)
mechanism design
(1)
domain randomization
(1)
latent representation
(1)
model architecture
(1)
preference modeling
(1)
language model
(1)
auction mechanism
(1)
preference elicitation
(1)
Papers
On scalable oversight with weak LLMs judging strong LLMs
NIPS 2024
Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders
NIPS 2024
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
EMNLP 2024
Tracr: Compiled Transformers as a Laboratory for Interpretability
NIPS 2023
A Neural Network Auction For Group Decision Making Over a Continuous Space
IJCAI 2021
Learning to Play No-Press Diplomacy with Best Response Policy Iteration
NIPS 2020
Relational Forward Models for Multi-Agent Learning
ICLR 2019
Reinforcement and Imitation Learning for Diverse Visuomotor Skills
RSS 2018
A Generalized-Zero-Preserving Method for Compact Encoding of Concept Lattices
ACL 2010