Benjamin Rosman
14 papers · 2017–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Academic Marathon (8) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (5) π£ Hot Topic Early Bird
π
Academic Marathon
(8)
π£
Hot Topic Early Bird
π
Cross-Pollinator
(13)
π
Keyword Champion
(2)
π§¬
Topic Evolution
π
Century Club
(14)
π
Conference Pioneer
Conferences
ICLR (6)
ICML (3)
NIPS (3)
ACL (1)
EMNLP (1)
Top co-authors
Keywords
transition dynamics
(2)
policy learning
(2)
transfer learning
(2)
low-resource language
(2)
reinforcement learning
(2)
speech processing
(1)
multilingual nlp
(1)
zero-shot learning
(1)
hierarchical reinforcement learning
(1)
skill composition
(1)
markov decision process
(1)
value function
(1)
temporal abstraction
(1)
boolean algebra
(1)
multitask learning
(1)
distributed representation
(1)
zero-shot transfer
(1)
automatic speech recognition
(1)
natural language processing
(1)
neural network architecture
(1)
Papers
Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks
ICLR 2025
The Esethu Framework: Reimagining Sustainable Dataset Governance and Curation for Low-Resource Languages
ACL 2025
The Zenoβs Paradox of βLow-Resourceβ Languages
EMNLP 2024
Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning
ICLR 2024
On The Specialization of Neural Modules
ICLR 2023
Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies
NIPS 2023
Generalisation in Lifelong Reinforcement Learning through Logical Composition
ICLR 2022
Autonomous Learning of Object-Centric Abstractions for High-Level Planning
ICLR 2022
Learning Portable Representations for High-Level Planning
ICML 2020
A Boolean Task Algebra for Reinforcement Learning
NIPS 2020
Composing Value Functions in Reinforcement Learning
ICML 2019
Hierarchical Subtask Discovery with Non-Negative Matrix Factorization
ICLR 2018
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning
NIPS 2018
Hierarchy Through Composition with Multitask LMDPs
ICML 2017