Parsa Kavehzadeh
3 papers · 2023–2025 · 2 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
(12)
Top co-authors
Research topics
Keywords
dynamic inference
(2)
model compression
(2)
multimodal learning
(1)
visual reasoning
(1)
neural network optimization
(1)
efficient computing
(1)
computational efficiency
(1)
early exit
(1)
language model
(1)
vision-language model
(1)
generative language model
(1)
chart comprehension
(1)
intermediate layer
(1)
chart question answering
(1)
large language model
(1)
knowledge distillation
(1)
Papers
Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models
EMNLP 2025
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference
EACL 2024
UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning
EMNLP 2023