Hosein Mohebbi
11 papers · 2021–2025 · 5 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (19) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver ❓ The Questioner (2)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
Top co-authors
Research topics
Deep Learning
(8)
Artificial Intelligence
(7)
Core AI
(7)
Machine Learning
(5)
Architectures
(5)
Natural Language Processing
(3)
Learning Types
(3)
Speech & Audio
(2)
Core Methods
(2)
Optimization & Theory · Deep Learning
(2)
Optimization & Theory · Machine Learning
(2)
Understanding
(2)
Analysis
(1)
Application Areas
(1)
Generation
(1)
Keywords
context mixing
(2)
model interpretability
(2)
probing analysis
(2)
representation learning
(1)
syntactic analysis
(1)
feature attribution
(1)
speech recognition
(1)
efficient computing
(1)
linguistic knowledge
(1)
inference optimization
(1)
neural network analysis
(1)
speech classification
(1)
layer-wise analysis
(1)
pre-trained model
(1)
knowledge transfer
(1)
mechanistic interpretability
(1)
token pruning
(1)
inference speedup
(1)
transformer encoder
(1)
transformer architecture
(1)
Papers
Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models
EMNLP 2025
On the reliability of feature attribution methods for speech classification
Interspeech 2025
What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training
Interspeech 2025
DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers
NAACL 2024
How Language Models Prioritize Contextual Grammatical Cues?
EMNLP 2024
Transformer-specific Interpretability
EACL 2024
Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers
EMNLP 2023
Quantifying Context Mixing in Transformers
EACL 2023
AdapLeR: Speeding up Inference by Adaptive Length Reduction
ACL 2022
Exploring the Role of BERT Token Representations to Explain Sentence Probing Results
EMNLP 2021
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations
EMNLP 2021