János Kramár
9 papers · 2010–2024 · 6 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (21) 🐣 Hot Topic Early Bird
🗃️
Keyword Collector
(51)
Top co-authors
Research topics
Keywords
multi-agent system
(3)
neural network
(2)
sparse autoencoder
(2)
model analysis
(2)
deep reinforcement learning
(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)
preference modeling
(1)
model architecture
(1)
preference elicitation
(1)
latent representation
(1)
language model
(1)
relational reasoning
(1)
Papers
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
EMNLP 2024
Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders
NeurIPS 2024
On scalable oversight with weak LLMs judging strong LLMs
NeurIPS 2024
Tracr: Compiled Transformers as a Laboratory for Interpretability
NeurIPS 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
NeurIPS 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