Amit Parekh
6 papers · 2023–2025 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
❓
The Questioner
🌈
Renaissance Researcher
(5)
Venues
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI · Artificial Intelligence
(5)
Machine Learning
(3)
Learning Types · Machine Learning
(3)
Deep Learning
(2)
Learning Types · Deep Learning
(2)
Computer Vision
(1)
Interdisciplinary
(1)
Natural Language Processing
(1)
Robotics
(1)
Application Areas
(1)
Applications · Robotics
(1)
Applications · Natural Language Processing
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Keywords
annotator disagreement
(2)
multimodal learning
(2)
embodied ai
(2)
robotic manipulation
(2)
vision-language model
(2)
multi-task learning
(2)
instruction tuning
(1)
action prediction
(1)
semantic clustering
(1)
transformer policy
(1)
jailbreak attack
(1)
multimodal model
(1)
latent embedding
(1)
perspective modeling
(1)
input perturbation
(1)
transformer-based model
(1)
safety guardrail
(1)
large language model
(1)
soft labeling
(1)
language feedback
(1)
Papers
FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks
EMNLP 2025
Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks
EMNLP 2024
Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks
COLING 2024
Voices in a Crowd: Searching for clusters of unique perspectives
EMNLP 2024
iLab at SemEval-2023 Task 11 Le-Wi-Di: Modelling Disagreement or Modelling Perspectives?
SemEval 2023
Multitask Multimodal Prompted Training for Interactive Embodied Task Completion
EMNLP 2023