Get started
Author

Kazuki Egashira

Observed names: Egashira, Kazuki, Kazuki EGASHIRA
OpenAlex ID: A5093625283
WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks
2025 · Miyai, Atsuyuki, Zhao, Zaiying, et al. · arXiv (Cornell University) · 33
PDF
JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation
2025 · Shota Onohara, Atsuyuki Miyai, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 12
PDF
Mind the Gap: A Practical Attack on GGUF Quantization
2025 · Egashira, Kazuki, Staab, Robin, et al. · arXiv (Cornell University) · 11
PDF
PULSE: Practical Evaluation Scenarios for Large Multimodal Model Unlearning
2025 · Kawakami, Tatsuki, Egashira, Kazuki, et al. · arXiv (Cornell University) · 10
PDF
Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR
2026 · Egashira, Kazuki, Vero, Mark, et al. · arXiv (Cornell University) · 7
PDF
MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding
2026 · Jeonghun Baek, Kazuki Egashira, et al. · Findings of the Association for Computational Linguistics: EACL · 7
Last Translation Benchmark
2026 · Zouhar, Vilém, Bafna, Niyati, et al. · Publikationen an der Universität Bielefeld (Universität Bielefeld) · 4
PDF
Fewer Weights, More Problems: A Practical Attack on LLM Pruning
2025 · Egashira, Kazuki, Staab, Robin, et al. · arXiv (Cornell University) · 4
PDF
All-in-One: A Composable Attack on LLM Transformations
2026 · Zhan, Xiaohua, Egashira, Kazuki, et al. · arXiv (Cornell University)
PDF
TestSuiteBench: Coding Agents Struggle to Generate Strong Test Suites from Specifications
2026 · Egashira, Kazuki, Mündler-Sasahara, Niels, et al. · arXiv (Cornell University)
PDF
Widening the Gap: Exploiting LLM Quantization via Outlier Injection
2026 · Zhan, Xiaohua, Egashira, Kazuki, et al. · arXiv (Cornell University)
PDF
AI Model Creation and System Verification of “Telemotion” Infrastructure-Cooperative Autonomous Driving System Using Digital Twin
2026 · Yasuyoshi Hatano, Noritsugu Iwazaki, et al. · SAE technical papers on CD-ROM/SAE technical paper series
MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding
2026 · Association for Computational Linguistics 2026, Aizawa, Kiyoharu, et al. · Underline Science Inc.
Negative Learning to Prevent Undesirable Misclassification
2023 · Kazuki EGASHIRA, Atsuyuki MIYAI, et al. · IEICE Transactions on Information and Systems
PDF
Works count: 17
Citation count: 172
H-index: 7
I10-index: 6
Year
Topic
Type