Atsuki Yamaguchi

atsuki-yamaguchi's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 7 days ago

Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability

Paper • 2610.03509 • Published 10 days ago • 17

upvoted a paper 11 days ago

Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior

Paper • 2609.39827 • Published 12 days ago • 13

upvoted a paper about 1 month ago

How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data

Paper • 2604.13977 • Published Apr 15 • 3

upvoted a paper 2 months ago

Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility

Paper • 2608.03930 • Published Aug 4 • 10

upvoted 2 papers 3 months ago

On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain

Paper • 2607.01444 • Published Jul 1 • 2

MultiHashFormer: Hash-based Generative Language Models

Paper • 2606.28057 • Published Jun 26 • 23

upvoted a paper 6 months ago

Where does output diversity collapse in post-training?

Paper • 2604.16027 • Published Apr 17 • 21

upvoted 2 papers 8 months ago

Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models

Paper • 2602.08658 • Published Feb 9 • 13

No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding

Paper • 2602.03709 • Published Feb 3 • 8

upvoted 3 papers 9 months ago

Olmo 3

Paper • 2512.13961 • Published Dec 15, 2025 • 38

An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift

Paper • 2601.05882 • Published Jan 9 • 21

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

Paper • 2601.03448 • Published Jan 6 • 13

upvoted a paper 10 months ago

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

Paper • 2512.04844 • Published Dec 4, 2025 • 5

upvoted a paper 12 months ago

Deconstructing Attention: Investigating Design Principles for Effective Language Modeling

Paper • 2510.11602 • Published Oct 13, 2025 • 15

upvoted 4 papers about 1 year ago

IntrEx: A Dataset for Modeling Engagement in Educational Conversations

Paper • 2509.06652 • Published Sep 8, 2025 • 26

Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language Models

Paper • 2507.11882 • Published Jul 16, 2025 • 1

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?

Paper • 2508.19827 • Published Aug 27, 2025 • 33

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Paper • 2508.07407 • Published Aug 10, 2025 • 100

upvoted a collection almost 2 years ago

Qwen2.5

Collection

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 43 items • Updated Mar 2 • 738