Skip to content
View fuvty's full-sized avatar
👋
👋
106 followers · 46 following

Achievements

Achievement: Pair Extraordinairex2Achievement: Starstruckx2Achievement: YOLOAchievement: Pull Sharkx2Achievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex2Achievement: Starstruckx2Achievement: YOLOAchievement: Pull Sharkx2Achievement: Quickdraw

Highlights

  • Pro

Organizations

@thu-nics @FatnessClub @dgSPARSE

Block or report fuvty

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
fuvty/README.md

Hi 👋

I’m Tianyu Fu (傅天予), a Ph.D. student at Tsinghua University, NICS-EFC Lab, supervised by Prof. Yu Wang. I obtained my bachelor’s degree from Tsinghua University in 2022.

My research interests lie in efficient long context large language models, check out our latest work here. Currently an intern at ByteDance Seed LLM model architecture team.

I welcome new friends and collaborators. Please don’t hesitate to reach out 🤗

Want to know more about me? Check out my Twitter, RedNote, or Profile. Feel free to explore featured projects from me and my amazing collaborators:

R2R
Token-level routing for reasoning LLMs 		TaH
Selective latent thinking for reasoning LLMs 		C2C
Communicate through KV-Cache between LLMs 		FrF
Efficient video token reduction for LVLMs 		MoA
Mixture of sparse attention for LLMs

Pinned Loading

  1. thu-nics/C2C thu-nics/C2C Public

    [ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"

    Python 414 52

  2. thu-nics/R2R thu-nics/R2R Public

    [NeurIPS'25] The official code implementation for paper "R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing"

    Python 93 13

  3. thu-nics/TaH thu-nics/TaH Public

    [ICML'26] Official implementation of paper "Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models"

    Python 74 11

  4. thu-nics/MoA thu-nics/MoA Public

    [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>

    Python 159 9

  5. thu-nics/FrameFusion thu-nics/FrameFusion Public

    [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"

    Python 76 3

  6. DeSCo DeSCo Public

    [WSDM'24 Oral] The official implementation of paper <DeSCo: Towards Generalizable and Scalable Deep Subgraph Counting>

    Python 24