Hi @KevinSRR 🤗
Niels here from the open-source team at Hugging Face. I discovered your work "A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents" through Hugging Face's daily papers, and your paper page is available here: https://huggingface.co/papers/2511.17208. The paper page allows people to discuss your research and find related artifacts (like your codebase or processed data), and you can also claim the paper as yours, which will show up on your public profile at HF, and add GitHub and project page URLs.
I saw in your GitHub README that you plan to open-source the EMem codebase on LoCoMo and LongMemEval benchmarks in December 2025. That's fantastic news! We'd be thrilled if you would consider hosting your EMem codebase on https://huggingface.co/models and any processed data (like the EDUs or graph structures) on https://huggingface.co/datasets once they are ready.
Hosting on Hugging Face will give your work more visibility and enable better discoverability. We can add tags to the model and dataset cards so that researchers can easily find and use your contributions, and link them directly to your paper page.
Uploading models (for the codebase)
You could consider pushing your EMem framework as a "model" repository, providing clear instructions for usage and showcasing its capabilities. See here for a guide: https://huggingface.co/docs/hub/models-uploading.
Uploading dataset (for processed EDUs/graphs)
If you plan to release the processed Elementary Discourse Units (EDUs) or graph structures as static data, making them available on 🤗 Datasets would be awesome! This would allow others to easily load them with:
from datasets import load_dataset
dataset = load_dataset("your-hf-org-or-username/your-emem-data")See here for a guide: https://huggingface.co/docs/datasets/loading. The dataset viewer also allows people to quickly explore the first few rows of the data in the browser.
We can also help you set up a Gradio demo on Spaces to showcase your LLM agent's long-term memory in action, and we can provide a ZeroGPU grant for free A100 GPUs.
Let me know if you're interested or need any guidance once your codebase and data are ready for release!
Cheers,
Niels
ML Engineer @ HF 🤗
Hi @KevinSRR 🤗
Niels here from the open-source team at Hugging Face. I discovered your work "A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents" through Hugging Face's daily papers, and your paper page is available here: https://huggingface.co/papers/2511.17208. The paper page allows people to discuss your research and find related artifacts (like your codebase or processed data), and you can also claim the paper as yours, which will show up on your public profile at HF, and add GitHub and project page URLs.
I saw in your GitHub README that you plan to open-source the EMem codebase on LoCoMo and LongMemEval benchmarks in December 2025. That's fantastic news! We'd be thrilled if you would consider hosting your EMem codebase on https://huggingface.co/models and any processed data (like the EDUs or graph structures) on https://huggingface.co/datasets once they are ready.
Hosting on Hugging Face will give your work more visibility and enable better discoverability. We can add tags to the model and dataset cards so that researchers can easily find and use your contributions, and link them directly to your paper page.
Uploading models (for the codebase)
You could consider pushing your EMem framework as a "model" repository, providing clear instructions for usage and showcasing its capabilities. See here for a guide: https://huggingface.co/docs/hub/models-uploading.
Uploading dataset (for processed EDUs/graphs)
If you plan to release the processed Elementary Discourse Units (EDUs) or graph structures as static data, making them available on 🤗 Datasets would be awesome! This would allow others to easily load them with:
See here for a guide: https://huggingface.co/docs/datasets/loading. The dataset viewer also allows people to quickly explore the first few rows of the data in the browser.
We can also help you set up a Gradio demo on Spaces to showcase your LLM agent's long-term memory in action, and we can provide a ZeroGPU grant for free A100 GPUs.
Let me know if you're interested or need any guidance once your codebase and data are ready for release!
Cheers,
Niels
ML Engineer @ HF 🤗