Babak Ehteshami Bejnordi
@BabakEht
Followers
344
Following
1K
Media
6
Statuses
107
Research Scientist@Qualcomm AI Research: Deep learning, Conditional computation, Model Efficiency, LLM/Vision
The Netherlands
Joined October 2012
RT @pimdehaan: Our paper got a prize :).Cheers to lead author @johannbrehmer, and fellow co-authors Sönke Behrends, and @TacoCohen. Our res….
0
13
0
RT @Renee42581826: I'll be presenting CLUES🔍 at #NeurIPS2024 in person! .Catch us at the poster session on: .⏰ Wed, Dec 11, 4:30–7:30 PM P….
0
7
0
RT @avskliar: 🚀 Excited to share our latest work "Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding" now on arXiv! We'….
arxiv.org
Large language models (LLMs) have become ubiquitous in practice and are widely used for generation tasks such as translation, summarization and instruction following. However, their enormous size...
0
14
0
RT @QCOMResearch: QIF Europe is an excellence award through which @Qualcomm rewards and mentors the most innovative PhD students in Europe….
0
7
0
We propose a dynamic tokenizer for ViTs, where the scale at which an image is processed varies based on the complexity of the image area. This means less computing for simple areas and more for complex, cluttered areas. Thanks to @royaleerieme, @JakobHavtorn, @TiRune.
MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers. paper page: The input tokens to Vision Transformers carry little semantic meaning as they are defined as regular equal-sized patches of the input image, regardless of its content. However,
0
8
48
RT @arankomatsuzaki: The case for 4-bit precision: k-bit Inference Scaling Laws. Shows that 4-bit precision is almost universally optimal f….
0
41
0
If you are at #NeurIPS2022, come visit us at the Qualcomm booth to check out our Expo Track demo: Conditional compute for on-device video understanding via @YouTube.
0
2
5
RT @QCOMResearch: Curious about what @Qualcomm #AI Research has in store at #NeurIPS2022? Learn about our latest demos, papers, workshops,….
qualcomm.com
Uncover the latest in AI research from Qualcomm at NeurIPS 2022. Discover platform enhancements and fundamental breakthroughs in machine learning.
0
7
0
RT @QCOMResearch: Qualcomm #AI Research is guided by purposeful innovation, passionate execution, and openness. Learn more: .
qualcomm.com
Meet the researchers bringing AI to the connected intelligent edge.
0
12
0
RT @TacoCohen: Really looking forward to this! We plan to release the lecture videos & course materials online.
0
16
0
RT @QCOMResearch: Want a glimpse at the future of #AI? Check out our latest accepted papers and research breakthroughs at upcoming conferen….
qualcomm.com
Here's a glimpse into the future of AI.
0
7
0
How many frames are needed to reliably recognize an action?.#FrameExit uses self-supervised gates to adjust the computation to the difficulty of the input video. Check out our #Oral #CVPR paper: #CVPR2021.Great collaboration with @ghodrati & @amir_habibian
4
5
36
RT @amir_habibian: Do we need to process every single pixel in a video?. TLDR: Compute the features only at the pixels that convey new info….
0
37
0
RT @pimdehaan: Very excited to present "Natural Graph Networks" at NeurIPS next week. We use naturality - a generalisation of equivariance….
0
41
0
RT @avskliar: Be sure to take a look at great papers and demos from @Qualcomm at #NeurIPS2020. Feel free to also tune in to #MLBites inter….
0
4
0
RT @aa_sadegh: I just gave a tutorial on latent variable models with the focus on Variational Autoencoders and Normalizing Flows as two way….
0
4
0
I was interviewed by @twimlai and we discussed our recent works at @Qualcomm #AI Research on conditional computation using gated neural nets. Thank you @samcharrington!. Here is the link:.
0
6
28
RT @twimlai: Today we’re joined by Babak Ehteshami Bejnordi (@BabakEht), a Research Scientist at @Qualcomm @Qualcomm_Tech, to discuss a few….
twimlai.com
0
8
0