Spaces:

---

huggingface

/

HuggingDiscussions

like 78

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

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

Regarding this feature @kramp , will there be future plans to integrate with Open Science Foundation preprints? Thinking for SocArXiv and others since they have the moderation workflow rather than the endorsement workflow. It could open things up for that part of the research community.

Hi, @akhaliq , @Kramp , @AdinaY

https://arxiv.org/abs/2603.05438 also meets {"error":"Arxiv paper not found"}

Can you take a look?

Thank you!

Hi, @akhaliq , @Kramp , @AdinaY

https://arxiv.org/abs/2603.05438 also meets {"error":"Arxiv paper not found"}

Can you take a look?

Thank you!

Hi @kdwon - The paper is now on the Daily Papers page: https://huggingface.co/papers/2603.05438
Feel free to claim it with your HF account, and start communicating with the community.