Rohin Shah
11 papers · 2019–2025 · 4 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 ↓+5 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (25) 🐣 Hot Topic Early Bird 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze
👑
Triple Crown
🧭
Keyword Pioneer
📈
Trend Setter
💎
Century Club · Bronze
🗃️
Keyword Collector
(55)
Venues
Top co-authors
Research topics
Artificial Intelligence
(10)
Machine Learning
(9)
Core AI
(9)
Learning Types · Machine Learning
(6)
Deep Learning
(3)
Reinforcement Learning
(2)
Architectures
(2)
Learning Paradigms
(2)
Optimization & Theory
(2)
Computer Science
(1)
Application Areas
(1)
Applications · Reinforcement Learning
(1)
Applications · Computer Science
(1)
Core Methods
(1)
Learning Types · Deep Learning
(1)
Keywords
reinforcement learning
(4)
reward function
(3)
inverse reinforcement learning
(2)
sparse autoencoder
(2)
imitation learning
(2)
large language model
(2)
multi-agent system
(2)
ai safety
(2)
human feedback
(2)
policy learning
(1)
markov decision process
(1)
behavior cloning
(1)
model evaluation
(1)
distribution shift
(1)
latent representation
(1)
preference learning
(1)
pairwise comparison
(1)
model analysis
(1)
reward learning
(1)
optimal policy
(1)
Papers
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
ICML 2025
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
BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
NeurIPS 2023
Learning What To Do by Simulating the Past
ICLR 2021
Optimal Policies Tend To Seek Power
NeurIPS 2021
The MAGICAL Benchmark for Robust Imitation
NeurIPS 2020
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference
ICML 2019
On the Utility of Learning about Humans for Human-AI Coordination
NeurIPS 2019
Preferences Implicit in the State of the World
ICLR 2019