Deep Learning

Hello, im submitting 4 suggestions: Subject 1: On exploiting transformers for detecting explicit song lyrics explanation: Detecting vulgar/offensive in song's lyrics paper link: click here subject 2: Prompt-to-Prompt Image Editing with Cross Attention Control links: https://arxiv.org/pdf/2208.0

Hi Tomer Me and my partner Tzahi Bakal would like to do our project about this topic: https://wzhouxiff.github.io/projects/MotionCtrl/ https://www.youtube.com/watch?v=2hfPVBDMB-o

Hi Tomer, We (Elior Malik & Sabeel Hamood) would like to present the MusicGen Model: https://www.youtube.com/watch?v=BRWquZdEigw Thank you.

Hello Tomer, We want to do our research and presentation about "Meta’s Llama3 AI", 2 minutes paper link: https://www.youtube.com/watch?v=8FFL86K4SfY Thanks.

Hi Tomer, During the last lecture, you talked about small language models, highlighting nanoGPT as a intriguing example. You mentioned that we could use the GitHub repository (https://github.com/karpathy/nanoGPT) and the YouTube video (https://www.youtube.com/watch?v=kCc8FmEb1nY) as our course proje

SUPIR (Scaling-UP Image Restoration), a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up. Leveraging multi-modal techniques and advanced generative prior, SUPIR marks a significant advance in intelligent and realistic image restoration. As a p

Hello Tomer, Me (Vladimir Brustinov) and Nik Lerman would like to present the following topic. https://paperswithcode.com/paper/llm-agent-operating-system The paper published 25 Mar 2024 and included code. Thank you!

Hello Tomer, We are Maxim Lebedinsky and Dmytri Kislitsyn. You have already accepted our suggested paper via email, but for formality, adding the paper again here. https://ai.google.dev/gemma/technical-report Thank you.

Hey Tomer! Me and Tal Cohen would like to present the following article: "Learning Soccer Juggling Skills with Layer-wise Mixture-of-Experts" Paper :https://www.cs.ubc.ca/~van/papers/2022-SIGGRAPH-juggle/soccer_juggling.pdf Code:https://github.com/ZhaomingXie/soccer_juggle_release Thanks!

Hello Tomer, I've talked to you about presenting a project about the paper "Attention is All You Need" Paper link: https://arxiv.org/pdf/1706.03762.pdf Thanks.

Hello Tomer, my name is Safwan Halabi, me and my partner Aharon Yonatayev want to suggest the following NLP project: Fake News Stance Detection Using Deep Learning Architecture (CNN-LSTM) https://www.sciencedirect.com/science/article/pii/S2667096820300070 https://ieeexplore.ieee.org/abstract/doc

Hi, we are Tal Gaon, Yovel Gabay and Ravid Goldin.

Hi Tomer, Me and my partner Nadav Cohen want to do our project on CoDi Video: https://www.youtube.com/watch?v=y1sxsye11xk&ab_channel=TwoMinutePapers Article: https://codi-gen.github.io/ Code: https://github.com/microsoft/i-Code/tree/main/i-Code-V3

Hi Tomer, Me and my partner Dorin Beery want to do our project on MotionCtrl Video: https://www.youtube.com/watch?v=2hfPVBDMB-o GitHub: https://github.com/TencentARC/MotionCtrl Paper also included published on the December 2023

Hi Tomer, We are Omri Cohen and Ilya Lev from the course Deep Learning for Computer Vision. We ask approval for project on "Gesture Generation from Speech". YouTube link: https://www.youtube.com/watch?v=Dt0cA2phKfU Article: https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.14734 Code: https://g

Hi, Tomer. We are Moayad Hamza and Rami Amasha, and we are thinking of making our project and presentation based on this video from "Two Minutes Paper": Microsoft’s New AI Clones Your Voice In 3 Seconds!,https://youtu.be/F6HSsVIkqIU?si=8NxSKYgjY71lXBDa Paper: "Neural Codec Language Models are Zero-

Hey Tomer, Our names are Yoni Azeraf & Ben Ben baruch, and we wanted to select the subject: the video: https://www.youtube.com/watch?v=k4k5RTNX-Js the paper: https://research.nvidia.com/labs/par/Perfusion/ the code: https://github.com/ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Persona

Hi Tomer, We are Shaked Arish and Yohan Leykin from the course Deep Learning for Computer Vision. We ask approval for project on "Communicative Agents for Software Development" Youtube link : https://www.youtube.com/watch?v=Zlgkzjndpak&t=11s Article : https://arxiv.org/pdf/2307.07924.pdf Code : htt

Hi tomer, Avishai hershkovitz and Vital Marciano SUPIR (Scaling-UP Image Restoration), a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up. Leveraging multi-modal techniques and advanced generative prior, SUPIR marks a significant advance in

Hello Tomer, Me (Dor Filis) and Hagar Tibi would like to present the following topic. https://rich-text-to-image.github.io/ The paper published 06 Dec 2023 and included code. Thank you!

Peleg Oanuno and Ron Lahiani. The project: DeepMind's AlphaFold 3 represents a groundbreaking advancement in computational biology and protein structure prediction. With its ability to accurately predict the 3D structures of proteins from their amino acid sequences, AlphaFold 3 has the potential to

Hi Tomer, We are Michael Ohayon and Ido Mialy from the course Deep Learning for Computer Vision. We would like to propose a project titled "Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild," abbreviated as "SUPIR." Here are some additional resourc

Hi Tomer, We would like to do our presentation about Phi-2 by Microsoft. This is the paper we found: https://www.microsoft.com/en-us/research/blog/phi-2-the-surprising-power-of-small-language-models/ Possible Codes: 1) https://colab.research.google.com/github/brevdev/notebooks/blob/main/phi2-finetun

Following our conversation in class here's the NLP project we want to present: https://paperswithcode.com/paper/exploiting-emotion-semantic-correlations-for Oded Morag Yaniv Lippa

Hi Tomer, We are Or Yosef and Yaniv Lippa from the course Deep Learning for Computer Vision. We ask approval for project on "Improving Fake News Video Detection by Correlating with Neighbors". Article: https://aclanthology.org/2023.findings-acl.756.pdf Git: https://github.com/ictmcg/fakesv

Hello Tomer, I've talked to you about presenting a project on the paper "Attention is all you need" Link to paper: https://arxiv.org/pdf/1706.03762.pdf Thanks.

Hi Tomer, My colleague Mario Rohana and I would like to present this topic: "Adversarial Diffusion Distillation" Youtube link: https://www.youtube.com/watch?v=Iol2rb65aSk Thank you, Ibrahim Daoud

Hi Tomer, me and my partner Adham Asaad are requesting approval to do a presentation on "Muse: Text-To-Image Generation via Masked Generative Transformers". Paper:https://arxiv.org/pdf/2301.00704.pdf Site: https://muse-model.github.io/ Thanks in advance Semion

Hi Tomer, We would like to do our final presentation on CodeFormer, based on the paper 'Towards Robust Blind Face Restoration with Codebook Lookup Transformer'. CodeFormer - Face Restoration Video: https://www.youtube.com/watch?v=pPCHSWCA4hg Code: https://github.com/sczhou/CodeFormer/tree/master Col

Hi Tomer , ilya and I would like to present on one of the articles below : option1 : Exploring the Effectiveness of Instruction Tuning in Biomedical Language Processing: [2401.00579] Exploring the Effectiveness of Instruction Tuning in Biomedical Language Processing (arxiv.org) Year - 31/12/23 op