Skip to content

Add Cache-to-Cache - Direct Semantic Communication Between LLMs #168

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add Cache-to-Cache - Direct Semantic Communication Between LLMs #168

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 23 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -836,6 +836,29 @@ Coding

</details>

## [Cache-to-Cache](https://github.com/thu-nics/C2C)
Direct semantic communication between LLMs via KV-Cache

<details>

![Image](https://raw.githubusercontent.com/thu-nics/C2C/main/resource/logo.png)

### Category
Multi-agent, Communication

### Description
- A novel paradigm for direct semantic communication between Large Language Models.
- Enables LLMs to communicate through KV-Cache instead of token sequences, avoiding information loss and generation latency.
- Uses a neural network to project and fuse the source model's KV-cache with the target model's cache for direct semantic transfer.

### Links
- [Project Page](https://fuvty.github.io/C2C_Project_Page/)
- [Paper](https://arxiv.org/abs/2510.03215)
- [GitHub](https://github.com/thu-nics/C2C)
- [HuggingFace](https://huggingface.co/collections/nics-efc/c2c-68e66ef54b977bd7e58d2d74)

</details>

## [Cal.ai](https://cal.ai)
Open-source scheduling assistant built on Cal.com

Expand Down