Nazia Tasnim
5 papers · 2022–2026 · 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
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(12)
โ
The Questioner
Venues
Top co-authors
Research topics
Keywords
model compression
(2)
zero-shot learning
(1)
benchmark evaluation
(1)
multilingual nlp
(1)
data augmentation
(1)
named entity recognition
(1)
incremental learning
(1)
automatic speech recognition
(1)
parameter sharing
(1)
low-resource language
(1)
foundation model
(1)
parameter-efficient fine-tuning
(1)
model ensemble
(1)
task adaptation
(1)
weight decomposition
(1)
cultural knowledge
(1)
multilingual model
(1)
weight factorization
(1)
dialect recognition
(1)
bengali language
(1)
Papers
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression
CVPR 2026
Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?
IJCNLP 2025
From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge
IJCNLP 2025
RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks
ICLR 2025
TEAM-Atreides at SemEval-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in Bangla
SemEval 2022