Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
Arsalan Zafar's picture
๐Ÿค Open to Collab

Arsalan Zafar PRO

ArsalanZ
5
ยท
https://www.arsalanzafar.ai/
  • ArsalanUk
  • arsalanzafar

AI & ML interests

LLMs, VLMs, Video Compression

Recent Activity

liked a model 3 days ago
Cactus-Compute/nemotron-3.5-120b-cq
reacted to Jiaqi-hkust's post with ๐Ÿง  3 days ago
We reshaped how VLMs connect vision to language! One simple architectural change โ†’ dramatically better visual information injection into the LLM. Accepted at NeurIPS. Check it out ๐Ÿ‘‡ ๐Ÿ“„ https://arxiv.org/abs/2611.06844 ๐Ÿ’ป https://github.com/YingyingYan1/DGP #NeurIPS #VLM #MLLM #ViT
reacted to kalyan-ks's post with ๐Ÿง  3 days ago
Replace k-means clustering algorithm with e-means algorithm Paper - https://arxiv.org/abs/2611.09501 Lloyd's k-means algorithm is a standard ML algorithm for clustering. This paper introduces e-means clustering algorithm which is [1] much faster than Lloyd k-means and [2] converges to lower losses, frequently even beating k-means++. On a wide array of embeddings datasets, it beats the loss of Lloyd k-means at 25 epochs in 1.4 to 2.6 epochs, As an example, e-means partitions DINO10B, a dataset of 10 billion DINO embeddings, into 16 million clusters in only 2.5 epochs, reaching a loss below Lloyd's at 25 epochs.
View all activity

Organizations

None yet

ArsalanZ 's datasets

None public yet
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs