小林 零

haruka87's activity

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

upvoted a paper 4 days ago

Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling

Paper • 2609.19499 • Published 8 days ago • 37

upvoted a paper 5 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 7 days ago • 177

upvoted a paper 8 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 17 days ago • 372

upvoted a paper 11 days ago

World in World: Explore the World with World Models

Paper • 2609.11548 • Published 14 days ago • 32

upvoted a paper 12 days ago

Generative Late-Interaction Embeddings For Visual Document Retrieval

Paper • 2609.11808 • Published 14 days ago • 27

published a model 13 days ago

haruka87/tight-warning-02db8e

Updated 13 days ago

liked a model 14 days ago

nex-agi/Nex-N2.5-mini

Text Generation • 35B • Updated 16 days ago • 8.99k • 841

liked a model 15 days ago

unsloth/Qwen3.8-Flash-Next-GGUF

Image-Text-to-Text • 177B • Updated 22 days ago • 1.79M • 1.06k

upvoted a paper 15 days ago

TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation

Paper • 2609.06665 • Published 18 days ago • 19

liked a model 19 days ago

BreezeBlue/Breeze-TTS-2

Text-to-Speech • 3B • Updated 15 days ago • 13.4k • 620