tokyotech-llm

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Tatsuya-Ichinose

authored a paper 4 months ago

Synthesizing Instruction-Tuning Datasets with Contrastive Decoding

Paper • 2604.13538 • Published Apr 15

published 4 models 4 months ago

tokyotech-llm/Medical-Qwen3-Swallow-30B-A3B

Text Generation • 31B • Updated Jun 15 • 270 • 9

tokyotech-llm/Medical-Qwen3-Swallow-32B

Text Generation • 33B • Updated Jun 15 • 113 • 1

tokyotech-llm/Medical-Qwen3-Swallow-8B

Text Generation • 8B • Updated Jun 15 • 834 • 4

tokyotech-llm/Medical-GPT-OSS-Swallow-120B

Text Generation • 117B • Updated Jun 15 • 221 • 6

updated 2 models 5 months ago

tokyotech-llm/Medical-GPT-OSS-Swallow-120B

Text Generation • 117B • Updated Jun 15 • 221 • 6

tokyotech-llm/Medical-Qwen3-Swallow-8B

Text Generation • 8B • Updated Jun 15 • 834 • 4

authored a paper 9 months ago

On the Optimal Reasoning Length for RL-Trained Language Models

Paper • 2602.09591 • Published Feb 10 • 6

authored a paper about 1 year ago

MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources

Paper • 2509.25531 • Published Sep 29, 2025 • 11

authored a paper about 1 year ago

Balancing Speed and Stability: The Trade-offs of FP8 vs. BF16 Training in LLMs

Paper • 2411.08719 • Published Nov 10, 2024 • 1

authored a paper about 1 year ago

Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

Paper • 2508.18672 • Published Aug 26, 2025 • 10

authored a paper over 1 year ago

Rewriting Pre-Training Data Boosts LLM Performance in Math and Code

Paper • 2505.02881 • Published May 5, 2025 • 7

authored a paper over 1 year ago

Rewriting Pre-Training Data Boosts LLM Performance in Math and Code

Paper • 2505.02881 • Published May 5, 2025 • 7

authored 5 papers over 1 year ago

Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models

Paper • 2503.23714 • Published Mar 31, 2025 • 2

Balancing Speed and Stability: The Trade-offs of FP8 vs. BF16 Training in LLMs

Paper • 2411.08719 • Published Nov 10, 2024 • 1

Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs

Paper • 2412.14471 • Published Dec 19, 2024

Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search

Paper • 2503.04412 • Published Mar 6, 2025 • 6

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

Paper • 2502.19261 • Published Feb 26, 2025 • 6

authored a paper over 1 year ago

ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability

Paper • 2502.11336 • Published Feb 17, 2025 • 1

authored a paper about 2 years ago

Agent Skill Acquisition for Large Language Models via CycleQD

Paper • 2410.14735 • Published Oct 16, 2024 • 2