Jayakumar Subramanian
5 papers · 2021–2026 · 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Academic Marathon ยท Sprint
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(11)
Venues
Top co-authors
Research topics
Keywords
reinforcement learning
(1)
offline reinforcement learning
(1)
policy gradient
(1)
sequential decision making
(1)
text-to-image generation
(1)
approximate planning
(1)
approximate dynamic programming
(1)
deep neural network
(1)
reward model
(1)
vision-language model
(1)
stable diffusion
(1)
length generalization
(1)
key-value cache
(1)
gated attention
(1)
dead-end state
(1)
trajectory encoding
(1)
partially observed system
(1)
sub-quadratic attention
(1)
risk identification
(1)
information state
(1)
Papers
Lizard: An Efficient Linearization Framework for Large Language Models
ACL 2026
Measuring And Improving Engagement of Text-to-Image Generation Models
ICLR 2025
Explaining RL Decisions with Trajectories
ICLR 2023
Approximate Information State for Approximate Planning and Reinforcement Learning in Partially Observed Systems
JMLR 2022
Medical Dead-ends and Learning to Identify High-Risk States and Treatments
NeurIPS 2021