Kazuki Egashira
4 papers · 2024–2026 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Venues
Top co-authors
Research topics
Keywords
adversarial attack
(2)
model quantization
(1)
post-training quantization
(1)
visual question answering
(1)
multimodal learning
(1)
projected gradient descent
(1)
large multimodal model
(1)
optical character recognition
(1)
quantized model
(1)
full-precision model
(1)
manga understanding
(1)
malicious behavior
(1)
llms
(1)
quantization
(1)
gguf
(1)
Papers
MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding
EACL 2026
JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation
NAACL 2025
Mind the Gap: A Practical Attack on GGUF Quantization
ICML 2025
Exploiting LLM Quantization
NeurIPS 2024