Mark A. Hasegawa-Johnson
9 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (6)
π
Cross-Pollinator
(11)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(16)
β
The Questioner
Conferences
INTERSPEECH (4)
ICLR (2)
ICML (2)
EMNLP (1)
Top co-authors
Keywords
multimodal learning
(2)
perceptual learning
(1)
speech recognition
(1)
neural machine translation
(1)
automatic speech recognition
(1)
speaker recognition
(1)
statistical machine translation
(1)
state space model
(1)
state-space model
(1)
long short-term memory
(1)
vision-language model
(1)
multimodal large language model
(1)
cross-attention mechanism
(1)
visual token compression
(1)
layer normalization
(1)
speech perception
(1)
token compression
(1)
lstm network
(1)
speech recognition error
(1)
end-to-end model
(1)
Papers
Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
ICLR 2025
ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
ICML 2025
Speech Self-Supervised Learning Using Diffusion Model Synthetic Data
ICML 2024
Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM
EMNLP 2024
C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
ICLR 2024
Learning Speaker Aware Offsets for Speaker Adaptation of Neural Networks
INTERSPEECH 2019
The Neural Correlates Underlying Lexically-Guided Perceptual Learning
INTERSPEECH 2019
Multimodal Word Discovery and Retrieval with Phone Sequence and Image Concepts
INTERSPEECH 2019
Study of the Performance of Automatic Speech Recognition Systems in Speakers with Parkinsonβs Disease
INTERSPEECH 2019