Fahim Tajwar
5 papers · 2022–2025 · 3 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
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(14)
โ
The Questioner
Venues
Top co-authors
Research topics
Keywords
image classification
(1)
sample efficiency
(1)
on-policy sampling
(1)
domain generalization
(1)
transfer learning
(1)
curriculum learning
(1)
data augmentation
(1)
human-robot interaction
(1)
class imbalance
(1)
invariance learning
(1)
continuous control
(1)
distribution shift
(1)
generative model
(1)
autonomous reinforcement learning
(1)
preference fine-tuning
(1)
layer-wise adaptation
(1)
human intervention
(1)
neural network
(1)
interaction data
(1)
categorical distribution
(1)
Papers
Training a Generally Curious Agent
ICML 2025
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
ICML 2024
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
ICLR 2023
Do deep networks transfer invariances across classes?
ICLR 2022
When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
NeurIPS 2022