Issa Sugiura

speed's activity

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

upvoted a collection about 21 hours ago

MoshiRAG Release

Collection

Candle & PyTorch model checkpoints released as part of the MoshiRAG release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi-rag • 2 items • Updated 1 day ago • 1

liked a model 17 days ago

llm-jp/llm-jp-4-vl-9b-beta

Feature Extraction • 9B • Updated 8 days ago • 1.94k • 12

published a model 17 days ago

llm-jp/llm-jp-4-vl-9b-beta

Feature Extraction • 9B • Updated 8 days ago • 1.94k • 12

updated a model 18 days ago

llm-jp/llm-jp-4-vl-9b-beta

Feature Extraction • 9B • Updated 8 days ago • 1.94k • 12

updated a dataset 19 days ago

llm-jp/WAON-Bench

Viewer • Updated 19 days ago • 1.87k • 360 • 2

updated a collection 19 days ago

Jagle

Collection

Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision–Language Models • 5 items • Updated 19 days ago • 1

liked 2 models 19 days ago

llm-jp/Llama-Mimi-8B

Audio-to-Audio • 8B • Updated Sep 19, 2025 • 54 • 12

llm-jp/Llama-Mimi-1.3B

Audio-to-Audio • 1B • Updated Oct 2, 2025 • 57 • 11

upvoted 2 collections 19 days ago

Llama-Mimi

Collection

Llama-Mimi: Speech Language Models with Interleaved Semantic and Acoustic Tokens • 3 items • Updated Sep 19, 2025 • 1

Jagle

Collection

Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision–Language Models • 5 items • Updated 19 days ago • 1

updated a collection 20 days ago

Jagle

Collection

Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision–Language Models • 5 items • Updated 19 days ago • 1

upvoted 2 papers 20 days ago

Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models

Paper • 2604.02048 • Published 30 days ago • 1

JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation

Paper • 2604.00909 • Published about 1 month ago • 1

updated a dataset 24 days ago

llm-jp/JAMMEval

Viewer • Updated 24 days ago • 1.59k • 764 • 5

authored 2 papers 24 days ago

JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation

Paper • 2604.00909 • Published about 1 month ago • 1

Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models

Paper • 2604.02048 • Published 30 days ago • 1

upvoted a collection 25 days ago

Gemma 4

Collection

8 items • Updated 29 days ago • 705

liked a dataset 26 days ago

llm-jp/JAMMEval

Viewer • Updated 24 days ago • 1.59k • 764 • 5

updated a collection 26 days ago

Multi Modal Models

Collection

6 items • Updated 25 days ago • 1

updated a collection about 1 month ago

Multi Modal Models

Collection

6 items • Updated 25 days ago • 1