Tianyu Fu

fuvty

·

https://fuvty.thesimple.ink/

AI & ML interests

efficient-llm large-language-models sparse-attention token-routing latent-iterations kv-cache multi-llm reasoning inference systems

Recent Activity

upvoted a collection about 3 hours ago

authored a paper 5 days ago

TokenRouter: Efficient Serving System for Token-Level LLM Routing

upvoted a paper 5 days ago

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

View all activity

Organizations

Papers 10

arxiv:2610.12242

arxiv:2609.35748

arxiv:2511.08577

arxiv:2510.03215

spaces 1

Cache-to-Cache Communication Demo

Compare Single, Text-to-Text, and Cache-to-Cache inference

models 0

None public yet

datasets 2

fuvty/tau-bench-synthetic

Viewer • Updated Apr 8 • 6.01k • 198 • 4

fuvty/mini-opd-deepmath

Viewer • Updated Apr 7 • 138k • 47