Spaces:

---

huggingface

/

HuggingDiscussions

like 76

Running

https://arxiv.org/abs/2406.01954

We are excited to share our recent work on MLLM architecture design titled "Ovis: Structural Embedding Alignment for Multimodal Large Language Model".

Paper: https://arxiv.org/abs/2405.20797
Github: https://github.com/AIDC-AI/Ovis
Model: https://huggingface.co/AIDC-AI/Ovis-Clip-Llama3-8B
Data: https://huggingface.co/datasets/AIDC-AI/Ovis-dataset

@Yiwen-ntu for now we support only videos as paper covers in the Daily.

we are excited to share our work titled "Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models" : https://arxiv.org/abs/2406.12644

Hi, @kramp !
Same issue here, our paper (https://arxiv.org/abs/2510.23515) cannot be submitted to Daily Papers due to the recency constraint (“This paper is more than 14 days old…”).
The issue is that our v1 was posted more than 14 days ago, but we just submitted v2 today — this is the full/complete version and the content has changed substantially compared to v1. We’re announcing the v2 release today and would really like it to be included in today’s Daily Papers.
Could you please advise whether the recency check can be based on the latest arXiv version date (v2) instead of the initial submission date? If so, would it be possible to manually allow / re-index paper 2510.23515 so we can submit it?

Thank you!

Hi @kramp !

I’m reaching out to see if it’s possible to manually allow or re-index our paper (https://arxiv.org/abs/2505.17001) for Daily Papers.

Currently, we are unable to submit it due to the 14-day recency constraint. While our v1 was posted some time ago as a submission draft, we have just released the v2 (the final version) today.

There are two major reasons why we believe it’s worth featuring now:

1. Significant Content Update: This v2 is the final version accepted by IEEE TPAMI, with substantial improvements and content changes compared to the initial v1.
2. Official Code Release: We have now officially released the code and established the project page, which was not available in the previous version.

Could you please advise if the recency check can be based on the latest v2 update date? If so, would it be possible to manually re-index paper [2505.17001] so we can share it with the community?

Hi @kramp @Sylvestre ,

Our paper (CloneMem: Benchmarking Long-Term Memory for AI Clones) was submitted to arXiv in early January but cannot be submitted to Daily Papers due to the recency constraint ("This paper is more than 14 days old...").
I'm an undergraduate student and this is my first paper on arXiv. I wasn't aware of the 7-day submission window for Daily Papers until now, and unfortunately missed the deadline.
CloneMem introduces a benchmark for evaluating AI clones' long-term memory capabilities using digital traces (diaries, social media posts) rather than conversational data, addressing an important gap in personalized AI evaluation.
Would it be possible to manually allow this paper to be submitted to Daily Papers? We believe it would be valuable for the HuggingFace community interested in AI personalization and memory systems.
Thank you so much for your help!

Paper title: CloneMem: Benchmarking Long-Term Memory for AI Clones
ArXiv ID: 2601.07023
HuggingFace username: ZhiyuZhangA

Hello @kramp @Sylvestre ,
I wanted to claim authorship to this paper https://huggingface.co/papers/2602.03359. However, it was denied.
So I added a secondary email, which is the email used in the author list of the paper.
I try to re-claim authorship, however, it says "You've already claimed authorship on this paper."

What should I do ?

Hi, HF team, @akhaliq , @Kramp @akhaliq

https://arxiv.org/abs/2602.08025 meets {"error":"Arxiv paper not found"}

How can I solve it?

Thank you!

Hi, HF team, @akhaliq , @Kramp @akhaliq

https://arxiv.org/abs/2602.08025 meets {"error":"Arxiv paper not found"}

How can I solve it?

Thank you!

Hi @weijiawu - Thanks for reaching out. The paper is now available on the paper page. Feel free to claim it with your HF account.

We propose DASH (Distributed Accelerated SHampoo), a faster and more accurate version of Distributed Shampoo.

To make it faster, we stack the blocks extracted from the preconditioners to obtain a 3D tensor, which are inverted efficiently using batch-matmuls via iterative procedures.

To make it more accurate, we introduce an existing iterative method from Numerical Linear Algebra called Newton-DB, which is more accurate than the existing Coupled Newton implemented in Distributed Shampoo.

These iterative procedures usually require the largest eigen-value of the input matrix to be upper bounded by 1, which should be obtained by scaling the input matrix. In theory, one should divide by the true largest eigen-value of the matrix, which is expensive to compute in Distributed Shampoo. Before our work, the simplest scaling was Frobenius norm, which is usually much larger than the largest eigen-value.

Since we work with all blocks in parallel in a stacked form, our implementation allows running Power-Iteration to estimate the largest eigen-value for all blocks in one shot. Why is this better?

When we scale the input matrix by Frobenius norm, the spectrum is shifted towards zero. We show that iterative procedures require more steps to converge for small eigen-values compared to larger ones. Therefore, scaling by an approximation of the largest eigen-value is desired and in our DASH implementation this is cheaper and therefore leads to faster training and more accurate models.

If you want to find out more, check out:
Paper: https://huggingface.co/papers/2602.02016
Code: https://github.com/IST-DASLab/DASH