Available now! Telegram Research 2025 — the year's key insights 
AI with Papers - Artificial Intelligence & Deep Learning
Open in Telegram
All the AI with papers. Every day fresh updates about #DeepLearning #MachineLearning #LLM & #ComputerVision Curated by Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/ #AI #chatGPT
Show more📈 Analytical overview of Telegram channel AI with Papers - Artificial Intelligence & Deep Learning
Channel AI with Papers - Artificial Intelligence & Deep Learning (@ai_deeplearning) in the English language segment is an active participant. Currently, the community unites 17 151 subscribers, ranking 7 726 in the Technologies & Applications category and 2 240 in the Malaysia region.
📊 Audience metrics and dynamics
Since its creation on невідомо, the project has demonstrated rapid growth, gathering an audience of 17 151 subscribers.
According to the latest data from 21 June, 2026, the channel demonstrates stable activity. Although there has been a change in the number of participants by -166 over the last 30 days and by -6 over the last 24 hours, overall reach remains high.
- Verification status: Not verified
- Engagement rate (ER): The average audience engagement rate is 23.63%. Within the first 24 hours after publication, content typically collects 6.86% reactions from the total number of subscribers.
- Post reach: On average, each post receives 4 057 views. Within the first day, a publication typically gains 1 177 views.
- Reactions and interaction: The audience actively supports content: the average number of reactions per post is 26.
- Thematic interests: Content is focused on key topics such as framework, object, dataset, tba, depth.
📝 Description and content policy
The author describes the resource as a platform for expressing subjective opinions:
“All the AI with papers. Every day fresh updates about #DeepLearning #MachineLearning #LLM & #ComputerVision
Curated by Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/
#AI #chatGPT”
Thanks to the high frequency of updates (latest data received on 22 June, 2026), the channel maintains relevance and a high level of publication reach. Analytics show that the audience actively interacts with content, making it an important point of influence in the Technologies & Applications category.
17 151
Subscribers
-624 hours
-277 days
-16630 days
Posts Archive
🖼️ Diffusive Images that Sound 🖼️
👉The University of Michigan unveils a diffusion model able to generate spectrograms that look like images but can also be played as sound.
👉Review https://t.ly/ADtYM
👉Paper arxiv.org/pdf/2405.12221
👉Project ificl.github.io/images-that-sound
👉Code github.com/IFICL/images-that-sound
⚽ 3D Shot Posture from Broadcast ⚽
👉Nagoya Univeristy unveils 3DSP soccer broadcast videos, the most extensive sports image dataset with 2D pose annotations EVER. Data and Source Code released💙
👉Review https://t.ly/IIMeZ
👉Paper https://arxiv.org/pdf/2405.12070
👉Code https://github.com/calvinyeungck/3D-Shot-Posture-Dataset/tree/master
🦕 Grounding DINO 1.5 Pro/Edge 🦕
👉Grounding DINO 1.5, a suite of advanced open-set object detection models to advanced the "Edge" of open-set object detection. Source Code released under Apache 2.0💙
👉Review https://t.ly/kS-og
👉Paper https://lnkd.in/dNakMge2
👉Code https://lnkd.in/djhnQmrm
🫀 EchoTracker: Tracking Echocardiography🫀
👉NTNU unveils EchoTracker, a two-fold coarse-to-fine model that facilitates the tracking of queried points on a tissue surface across ultrasound. Source Code released💙
👉Review https://t.ly/NyBe0
👉Paper https://arxiv.org/pdf/2405.08587
👉Code https://github.com/riponazad/echotracker/
🔥EfficientTrain++: Efficient Foundation Visual Backbone Training🔥
👉Tsinghua unveils EfficientTrain++, a simple, general, surprisingly effective, off-the-shelf approach to reduce the training time of various popular models (e.g., ResNet, ConvNeXt, DeiT, PVT, Swin, CSWin, and CAFormer). Up to 3.0× faster on ImageNet-1K/22K without sacrificing accuracy. Source Code released 💙
👉Review https://t.ly/D8ttv
👉Paper https://arxiv.org/pdf/2405.08768
👉Code https://github.com/LeapLabTHU/EfficientTrain
🪬UHM: Authentic Hand by Phone🪬
👉 META unveils UHM, novel 3D high-fidelity avatarization of your (yes, the your one) hand. Adaptation pipeline fits the pre-trained UHM via phone scan. Source Code released 💙
👉Review https://t.ly/fU5rA
👉Paper https://lnkd.in/dyGaiAnq
👉Code https://lnkd.in/d9B_XFAA
👻 3D Humans Motion from Text 👻
👉Zhejiang (+ANT) unveils a novel method to generate human motions containing accurate human-object interactions in 3D scenes based on textural descriptions. Code announced, coming 💙
👉Review https://t.ly/eOZnU
👉Paper https://arxiv.org/pdf/2405.07784
👉Project https://zju3dv.github.io/text_scene_motion/
🐏 AniTalker: Universal Self-Talking Humans 🐏
👉SJTU (+AISpeech) unveils AniTalker, a framework that transforms a single static portrait and input audio into animated talking videos with naturally flowing movements.
👉Review https://t.ly/MD4yX
👉Paper https://arxiv.org/pdf/2405.03121
👉Project https://x-lance.github.io/AniTalker/
👉Repo https://github.com/X-LANCE/AniTalker
💥FeatUp: Model at Any Resolution💥
👉FeatUp is a task- and model-agnostic framework to restore lost spatial information in deep features. It outperforms other feature upsampling in class activation map generation, transfer learning for segmentation and depth prediction, and end-to-end training for semantic segm. Source Code released💙
👉Review https://t.ly/Evq_g
👉Paper https://lnkd.in/gweaN4s6
👉Project https://lnkd.in/gWcGXdxt
👉Code https://lnkd.in/gweq5NY4
🔫 Free-Moving Reconstruction 🔫
👉EPFL (+#MagicLeap) unveils a novel approach for reconstructing free-moving object from monocular RGB clip. Free interaction with objects in front of a moving cam without relying on any prior, and optimizes the sequence globally without any segments. Great but no code announced🥺
👉Review https://t.ly/2xhtj
👉Paper arxiv.org/pdf/2405.05858
👉Project haixinshi.github.io/fmov/
🦑 Hyper-Detailed Image Descriptions 🦑
👉#Google unveils ImageInWords (IIW), a carefully designed HIL annotation framework for curating hyper-detailed image descriptions and a new dataset resulting from this process
👉Review https://t.ly/engkl
👉Paper https://arxiv.org/pdf/2405.02793
👉Repo https://github.com/google/imageinwords
👉Project https://google.github.io/imageinwords
👉Dataset huggingface.co/datasets/google/imageinwords
👉Explorer huggingface.co/spaces/google/imageinwords-explorer
🍏 XFeat: Neural Features Matching 🍏
👉XFeat (Accelerated Features) is lightweight/accurate architecture for efficient visual correspondence. It revisits fundamental design choices in CNN for detecting, extracting & matching local features
👉Review https://t.ly/ppb38
👉Paper arxiv.org/pdf/2404.19174
👉Code https://lnkd.in/dFzTpzN8
👉Project https://lnkd.in/d8JnV-iu
🏷️DiffMOT (#CVPR24): diffusion-MOT🏷️
👉DiffMOT is a novel real-time diffusion-based MOT approach to tackle the complex nonlinear motion. Impressive results & Source Code released💙
👉Review https://t.ly/ztlHi
👉Paper https://lnkd.in/d4K3c-nt
👉Project https://diffmot.github.io/
👉Code github.com/Kroery/DiffMOT
🌊 Diffusive 3D Human Recovery 🌊
👉The Rutgers University unveils ScoreHMR at #CVPR24; novel approach for 3D human pose and shape reconstruction. Impressive results.
👉Review https://t.ly/G0k2D
👉Paper https://arxiv.org/pdf/2403.09623
👉Code https://github.com/statho/ScoreHMR
👉Project https://statho.github.io/ScoreHMR/
🌐 3D Scenes with Depth Inpainting 🌐
👉Oxford announced two novel contributions to the field of 3D scene generation: a new benchmark and a novel depth completion model. 🤗-Demo and Source Code released💙
👉Review https://t.ly/BKiny
👉Paper https://arxiv.org/pdf/2404.19758
👉Project https://research.paulengstler.com/invisible-stitch/
👉Code https://github.com/paulengstler/invisible-stitch
👉Demo https://huggingface.co/spaces/paulengstler/invisible-stitch
🏝️1000x Scalable Neural 3D Fields🏝️
👉Highly-scalable neural 3D Fields: 1000x reductions in memory maintaining speed/quality: 10 MB vs. 10 GB! Code released 💙
👉Review https://t.ly/sLTK5
👉Paper https://lnkd.in/dEYM8-t2
👉Project https://lnkd.in/djptdujx
👉Code https://lnkd.in/dcCnFZ2n
🪷 Tunnel Try-on: SOTA VTON 🪷
👉"Tunnel Try-on", the first diffusion-based video virtual try-on model that demonstrates SOTA performance in complex scenarios. No code announced :(
👉Review https://t.ly/joMtJ
👉Paper arxiv.org/pdf/2404.17571
👉Project mengtingchen.github.io/tunnel-try-on-page/
👗TELA: Text to 3D Clothed Human👗
👉 TELA is a novel approach for the new task of clothing disentangled 3D human model generation from texts. This novel approach unleashes the potential of many downstream applications (e.g., virtual try-on).
👉Review https://t.ly/6N7JV
👉Paper https://arxiv.org/pdf/2404.16748
👉Project https://jtdong.com/tela_layer/
👉Code https://github.com/DongJT1996/TELA
🌊 FlowMap: dense depth video 🌊
👉MIT (+CSAIL) unveils FlowMap, a novel E2E differentiable method that solves for precise camera poses, camera intrinsics, and perframe dense depth of a video sequence. Source Code released 💙
👉Review https://lnkd.in/dMgakzWm
👉Paper arxiv.org/pdf/2404.15259.pdf
👉Project cameronosmith.github.io/flowmap
👉Code github.com/dcharatan/flowmap
🎡 NER-Net: Seeing at Nighttime 🎡
👉Huazhong (+Beijing) unveils a novel event-based nighttime imaging solution under non-uniform illumination, plus a paired multi-illumination level real-world dataset. Repo online, code coming 💙
👉Review https://t.ly/Z9JMJ
👉Paper arxiv.org/pdf/2404.11884.pdf
👉Repo github.com/Liu-haoyue/NER-Net
👉Clip https://www.youtube.com/watch?v=zpfTLCF1Kw4
