Atsuki Yamaguchi

atsuki-yamaguchi

48 19 96

alibayram's profile picture

XingweiT's profile picture

dark-pen's profile picture

https://gucci-j.github.io/about/

_gucciiiii
gucci-j

AI & ML interests

Natural Language Processing

Recent Activity

updated a model about 4 hours ago

verify-ppt/ppt-set_3b_v2

published a model about 4 hours ago

verify-ppt/ppt-set_3b_v2

updated a model about 5 hours ago

verify-ppt/ppt-code_3b

View all activity

Organizations

atsuki-yamaguchi 's collections 5

SSU: Source-Shielded Updates

Collection of models for "Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates"

Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates

Paper • 2512.04844 • Published Dec 4, 2025 • 5
ssu-project/OLMo-2-1124-7B-Instruct-am-random

7B • Updated Dec 6, 2025 • 5
ssu-project/OLMo-2-1124-7B-Instruct-am-magnitude

7B • Updated Dec 6, 2025 • 4
ssu-project/OLMo-2-1124-7B-Instruct-am-ssu

7B • Updated Dec 6, 2025 • 4

ElChat

Collection of models for "Adapting Chat Language Models Using Only Target Unlabeled Language Data" (TMLR 2025)

Vocabulary Expansion of Chat Models with Unlabeled Target Language Data

Paper • 2412.11704 • Published Dec 16, 2024
atsuki-yamaguchi/Qwen2.5-7B-bn-madlad-mean-cv

Text Generation • 8B • Updated Dec 6, 2025 • 12
atsuki-yamaguchi/Qwen2.5-7B-gu-madlad-mean-cv

Text Generation • 8B • Updated Dec 6, 2025 • 8
atsuki-yamaguchi/Qwen2.5-7B-te-madlad-mean-cv

Text Generation • 8B • Updated Dec 6, 2025 • 16

Cross-lingual Vocabulary Adaptation for Inference Speeups

Collection of models for "An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference" (EMNLP Findings 2024)

An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Generative LLM Inference

Paper • 2402.10712 • Published Feb 16, 2024
atsuki-yamaguchi/bloom-1b1-lapt-de

Updated Dec 6, 2025
atsuki-yamaguchi/bloom-7b1-random-ar

Text Generation • 6B • Updated Dec 5, 2025 • 8
atsuki-yamaguchi/bloom-7b1-random-de

Text Generation • 6B • Updated Dec 5, 2025 • 9

L2T: Pre-training with Language Learning Tasks

Collection of models for "Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks"

Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks

Paper • 2601.03448 • Published Jan 6 • 13

Low-resource Vocabulary Expansion

Collection of models for "How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?"

Vocabulary Expansion for Low-resource Cross-lingual Transfer

Paper • 2406.11477 • Published Jun 17, 2024
atsuki-yamaguchi/Llama-2-7b-hf-sw-30K-rand

Text Generation • 7B • Updated Dec 5, 2025 • 7
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-1000-rand-2x2ls-mtp-512

7B • Updated Dec 5, 2025 • 10
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-focus

Text Generation • 7B • Updated Dec 5, 2025 • 5

SSU: Source-Shielded Updates

Collection of models for "Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates"

Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates

Paper • 2512.04844 • Published Dec 4, 2025 • 5
ssu-project/OLMo-2-1124-7B-Instruct-am-random

7B • Updated Dec 6, 2025 • 5
ssu-project/OLMo-2-1124-7B-Instruct-am-magnitude

7B • Updated Dec 6, 2025 • 4
ssu-project/OLMo-2-1124-7B-Instruct-am-ssu

7B • Updated Dec 6, 2025 • 4

L2T: Pre-training with Language Learning Tasks

Collection of models for "Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks"

Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks

Paper • 2601.03448 • Published Jan 6 • 13

ElChat

Collection of models for "Adapting Chat Language Models Using Only Target Unlabeled Language Data" (TMLR 2025)

Vocabulary Expansion of Chat Models with Unlabeled Target Language Data

Paper • 2412.11704 • Published Dec 16, 2024
atsuki-yamaguchi/Qwen2.5-7B-bn-madlad-mean-cv

Text Generation • 8B • Updated Dec 6, 2025 • 12
atsuki-yamaguchi/Qwen2.5-7B-gu-madlad-mean-cv

Text Generation • 8B • Updated Dec 6, 2025 • 8
atsuki-yamaguchi/Qwen2.5-7B-te-madlad-mean-cv

Text Generation • 8B • Updated Dec 6, 2025 • 16

Low-resource Vocabulary Expansion

Collection of models for "How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?"

Vocabulary Expansion for Low-resource Cross-lingual Transfer

Paper • 2406.11477 • Published Jun 17, 2024
atsuki-yamaguchi/Llama-2-7b-hf-sw-30K-rand

Text Generation • 7B • Updated Dec 5, 2025 • 7
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-1000-rand-2x2ls-mtp-512

7B • Updated Dec 5, 2025 • 10
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-focus

Text Generation • 7B • Updated Dec 5, 2025 • 5

Cross-lingual Vocabulary Adaptation for Inference Speeups

Collection of models for "An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference" (EMNLP Findings 2024)

An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Generative LLM Inference

Paper • 2402.10712 • Published Feb 16, 2024
atsuki-yamaguchi/bloom-1b1-lapt-de

Updated Dec 6, 2025
atsuki-yamaguchi/bloom-7b1-random-ar

Text Generation • 6B • Updated Dec 5, 2025 • 8
atsuki-yamaguchi/bloom-7b1-random-de

Text Generation • 6B • Updated Dec 5, 2025 • 9