Mahdieh Soleymani Baghshah
16 papers · 2019–2026 · 8 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (41) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint 𧬠Topic Evolution
ποΈ
Keyword Collector
(102)
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(6)
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(12)
Deep Learning
(11)
Core AI
(11)
Machine Learning
(9)
Natural Language Processing
(7)
Core Methods
(5)
Models
(5)
Optimization & Theory
(5)
Resources & Methods
(5)
Architectures
(3)
Learning Types Β· Deep Learning
(3)
Learning Types Β· Machine Learning
(3)
Techniques
(2)
Computer Vision
(1)
Interdisciplinary
(1)
Keywords
large language model
(3)
vision-language model
(3)
persian language
(2)
attention mechanism
(2)
text generation
(2)
feature attribution
(2)
domain generalization
(1)
vision transformer
(1)
transformer architecture
(1)
visual question answering
(1)
argument mining
(1)
mathematical reasoning
(1)
uncertainty quantification
(1)
text editing
(1)
benchmark evaluation
(1)
bias detection
(1)
multimodal learning
(1)
text classification
(1)
paraphrase generation
(1)
multilingual nlp
(1)
Papers
MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment
EACL 2026
Understanding Counting Mechanisms in Large Language and Vision-Language Models
CVPR 2026
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation
ACL 2025
CER: Confidence Enhanced Reasoning in LLMs
ACL 2025
CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation
CVPR 2025
ELAB: Extensive LLM Alignment Benchmark in Persian Language
ACL 2025
LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions
CVPR 2025
Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models
ECCV 2024
Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
CVPR 2024
RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples
ICML 2024
SOInter: A Novel Deep Energy-Based Interpretation Method for Explaining Structured Output Models
ICLR 2024
Sina at SemEval-2023 Task 4: A Class-Token Attention-based Model for Human Value Detection
SemEval 2023
MG-BERT: Multi-Graph Augmented BERT for Masked Language Modeling
NAACL 2021
Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
ICML 2021
Paraphrase Generation by Learning How to Edit from Samples
ACL 2020
Jointly Measuring Diversity and Quality in Text Generation Models
NAACL 2019