NEW BOT Телеграм, страница - 200607592

ML Research Hub

32.7K subscribers

4.01K photos

229 videos

23 files

4.32K links

Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho

Download Telegram

About

Blog

Apps

Platform

ML Research Hub

32.7K subscribers

ML Research Hub

This media is not supported in your browser

VIEW IN TELEGRAM

🌟

VADER – video diffusion alignment via reward gradient

VADER is a method for aligning the results of diffusion models for video generation;
VADER allows to improve various models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion using different approaches such as HPS, PickScore, VideoMAE, VJEPA, YOLO, Aesthetics and others.

🖥

🟡

VADER page

🌐 https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

Please open Telegram to view this post

VIEW IN TELEGRAM

👍5❤2

3.49K views08:11

ML Research Hub

DeepInteraction & DeepInteraction++

🖥

Github: https://github.com/fudan-zvg/deepinteraction

📕

Paper: https://arxiv.org/abs/2408.05075v1

🚀 Dataset: https://paperswithcode.com/dataset/nuscenes

Please open Telegram to view this post

VIEW IN TELEGRAM

👍3

3.11K viewsedited 14:04

ML Research Hub

Forwarded from 🐳

🐋

WHALE — TOKEN, NFT, AND A BRIGHT FUTURE AHEAD

🐋

Exciting News, Friends!

🚀

@whale has just unveiled their new roadmap, and it’s packed with potential! According to their plans, the value of their NFT is set to rise significantly in the near future

🐳

📈

And that’s not all! They’re also hosting an airdrop of 10 million $Whale tokens,💰 which you can claim right now!

⭐️

Claim Your Share:

🟠

Referral System: Earn tokens by inviting friends to join.

🟠

Winnings (Coming Soon): Every $1 you win = $1Whale!

If you are not with them yet, now is the perfect time to join! 👇

Please open Telegram to view this post

VIEW IN TELEGRAM

❤2👍2🏆1

2.15K views11:39

🔥 Join now 🔥

ML Research Hub

Paper Name: The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

Paper: https://arxiv.org/pdf/2408.06292v2.pdf

Code: https://github.com/sakanaai/ai-scientist

🌐 https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

👍2

2.33K viewsedited 05:28

ML Research Hub

Zero-Shot Surgical Tool Segmentation in Monocular Video Using Segment Anything Model 2

Paper: https://arxiv.org/pdf/2408.01648v1.pdf

Code: https://github.com/AngeLouCN/SAM-2_Surgical_Video

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

👍1

2.24K viewsedited 05:35

ML Research Hub

MooER: LLM-based Speech Recognition and Translation Models from Moore Threads

Paper: https://arxiv.org/pdf/2408.05101v1.pdf

Code: https://github.com/moorethreads/mooer

Datasets: https://github.com/kaldi-asr/kaldi/tree/master/egs/aishell2

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

1.96K viewsedited 06:01

ML Research Hub

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

Paper: https://arxiv.org/pdf/2408.04810v1.pdf

Code: https://github.com/facebookresearch/unibench

Datasets: https://www.cs.toronto.edu/~kriz/cifar.html

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

1.82K viewsedited 06:06

ML Research Hub

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Paper: https://arxiv.org/pdf/2408.02900v1.pdf

Code: https://github.com/UCSC-VLAA/MedTrinity-25M

Datasets: https://yunfeixie233.github.io/MedTrinity-25M/

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

1.96K viewsedited 06:13

ML Research Hub

DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

Paper: https://arxiv.org/pdf/2408.08152v1.pdf

Code: https://github.com/deepseek-ai/deepseek-prover-v1.5

Datasets: https://github.com/zhangir-azerbayev/ProofNet

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

1.75K viewsedited 06:38

ML Research Hub

Rethinking Medical Anomaly Detection in Brain MRI: An Image Quality Assessment Perspective

Paper: https://arxiv.org/pdf/2408.08228v1.pdf

Code: https://github.com/zx-pan/medanomalydetection-iqa

Datasets: http://braintumorsegmentation.org/ || https://brain-development.org/ixi-dataset/

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

1.83K viewsedited 06:45

ML Research Hub

HAIR: Hypernetworks-based All-in-One Image Restoration

Paper: https://arxiv.org/pdf/2408.08091v1.pdf

Code: https://github.com/toummHus/HAIR

Datasets: https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/bsds/ ||https://seungjunnah.github.io/Datasets/gopro

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

2.03K viewsedited 06:50

ML Research Hub

MambaMIM: Pre-training Mamba with State Space Token-interpolation

Paper: https://arxiv.org/pdf/2408.08070v1.pdf

Code: https://github.com/fenghetan9/mambamim

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

1.97K views06:51

ML Research Hub

ChatGPT Telegram Bot: GPT-4o. Fast. No daily limits.

Group Chat support (/help_group_chat to get instructions) Voice message recognition Code highlighting. Write code with AI!

15 special chat modes:

👩🏼‍🎓 Assistant,
👩🏼‍💻 Code Assistant,
👩‍🎨 Artist,
🧠 Psychologist,
🚀 Elon Musk and other

2.23K views06:53

ML Research Hub

BadMerging: Backdoor Attacks Against Model Merging

Paper: https://arxiv.org/pdf/2408.07362v1.pdf

Code: https://github.com/jzhang538/badmerging

Datasets: ImageNet ||CIFAR-100 || SVHN || EuroSAT

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

❤1👍1

2.56K views08:54

ML Research Hub

ML Research Hub

BadMerging: Backdoor Attacks Against Model Merging Paper: https://arxiv.org/pdf/2408.07362v1.pdf Code: https://github.com/jzhang538/badmerging Datasets: ImageNet ||CIFAR-100 || SVHN || EuroSAT https://news.1rj.ru/str/DataScienceT ⭐️

If the articles we publish have changed your life, then kindly interact with the books using Telegram stars ⭐️

2.22K views17:21

ML Research Hub

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

Paper: https://arxiv.org/pdf/2408.06292v2.pdf

Code: https://github.com/sakanaai/ai-scientist

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

2.22K viewsedited 05:56

ML Research Hub

ControlNeXt: Powerful and Efficient Control for Image and Video Generation

Paper: https://arxiv.org/pdf/2408.06070v2.pdf

Code: https://github.com/dvlab-research/controlnext

Datasets: https://laion.ai/blog/laion-5b/

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

2K viewsedited 05:59

ML Research Hub

2e8dd625_3527_4643_86b6_3b96575881a9.gif

MindSearch: Mimicking Human Minds Elicits Deep AI Searcher

Paper: https://arxiv.org/pdf/2407.20183v1.pdf

Code: https://github.com/internlm/mindsearch

Datasets: HotpotQA || Bamboogle

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

1.92K viewsedited 06:10

ML Research Hub

This media is not supported in your browser

VIEW IN TELEGRAM

MixTex: Unambiguous Recognition Should Not Rely Solely on Real Data

Paper: https://arxiv.org/pdf/2406.17148v2.pdf

Code: https://github.com/RQLuo/MixTeX

https://news.1rj.ru/str/DataScienceT

⭐️

Please open Telegram to view this post

VIEW IN TELEGRAM

👍1

1.96K viewsedited 06:17