AI with Papers - Artificial Intelligence & Deep Learning
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
Показати більше📈 Аналітичний огляд Telegram-каналу AI with Papers - Artificial Intelligence & Deep Learning
Канал AI with Papers - Artificial Intelligence & Deep Learning (@ai_deeplearning) у мовному сегменті Англійська є активним учасником. На даний момент спільнота об'єднує 17 021 підписників, посідаючи 7 397 місце в категорії Технології та додатки та 2 168 місце у регіоні Малайзія.
📊 Показники аудиторії та динаміка
З моменту свого створення невідомо, проект продемонстрував стрімке зростання, зібравши аудиторію у 17 021 підписників.
За останніми даними від 14 вересня, 2026, канал демонструє стабільну активність. Хоча за останні 30 днів спостерігається зміна кількості учасників на -4, а за останні 24 години на -3, загальне охоплення залишається високим.
- Статус верифікації: Не верифікований
- Рівень залученості (ER): Середній показник залученості аудиторії становить 20.67%. Протягом перших 24 годин після публікації контент зазвичай збирає 6.90% реакцій від загальної кількості підписників.
- Охоплення публікацій: В середньому кожен допис отримує 3 518 переглядів. Протягом першої доби публікація в середньому набирає 1 174 переглядів.
- Реакції та взаємодія: Аудиторія активно підтримує контент: середня кількість реакцій на один пост – 15.
- Тематичні інтереси: Контент зосереджений навколо ключових тем, таких як framework, object, dataset, tba, depth.
📝 Опис та контентна політика
Автор описує ресурс як майданчик для висловлення суб'єктивної думки:
“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”
Завдяки високій частоті оновлень (останні дані отримано 15 вересня, 2026), канал підтримує актуальність та високий рівень охоплення публікацій. Аналітика показує, що аудиторія активно взаємодіє з контентом, що робить його важливою точкою впливу в категорії Технології та додатки.
Триває завантаження даних...
| Дата | Залучення підписників | Згадування | Канали | |
| 15 вересня | 0 | |||
| 14 вересня | +4 | |||
| 13 вересня | +1 | |||
| 12 вересня | +1 | |||
| 11 вересня | +5 | |||
| 10 вересня | +4 | |||
| 09 вересня | 0 | |||
| 08 вересня | +2 | |||
| 07 вересня | +1 | |||
| 06 вересня | +3 | |||
| 05 вересня | +4 | |||
| 04 вересня | +4 | |||
| 03 вересня | +8 | |||
| 02 вересня | +5 | |||
| 01 вересня | 0 |
| 2 | 🦺Efficient/Scalable Video Pretraining🦺
👉LeVJEPA1 (Yann Lecun) is the first video encoder trained under LeJEPA’s collapse-free objective, and evaluate it under frozen probing against video and image pretraining baselines retrained on identical data, in both epoch-matched and FLOP-matched regimes. Repo under MIT💙
👉Review https://lnkd.in/p/eJQAm3AN
👉Paper https://lnkd.in/eCzzTiNH
👉Project https://levjepa.github.io/
👉Repo https://lnkd.in/etiF5CDj | 1 870 |
| 3 | 🔥🔥 Marigold V2 is out 🔥🔥
👉Marigold V2 is out: depth, (impressive) see-through depth, surface normals, albedo, and other dense modalities. SOTA results. Repo under Apache 2.0💙
#AI #deeplearning #AIwithPapers
👉Review https://lnkd.in/p/eKM44yDQ
👉Paper https://arxiv.org/pdf/2609.08084
👉Repo https://github.com/huawei-bayerlab/marigold-v2
👉Project https://huggingface.co/spaces/huawei-bayerlab/marigold-v2-web | 2 192 |
| 4 | 🏀McByte++ tracking-by-detection🏀
👉McByte++ is the newer extension of McByte that advances training-free sports MOT toward long-term ID tracking, while simultaneously improving efficiency and runtime performance. Repo under Apache 2.0💙
👉Review https://lnkd.in/p/e4-diVJS
👉Paper https://lnkd.in/e_Vxky-b
👉Repo https://lnkd.in/e8SeCYmk | 2 165 |
| 5 | 🔥 #AIwithPapers: we are 17,000+ 🔥
👉 Even though 100+ bots are trying to join the discussion chats every day, there are 17,000 of us! Almost all of us are still humans 🧟
😈 Invite -> https://t.me/AI_DeepLearning | 2 417 |
| 6 | 👻Emerging Objs from Motion👻
👉Motion boundaries provide a strong signal for object-level grouping and can be used to derive pseudo-instance supervision. Suitable for: mono-depth, 3D object detection, 3D occupancy, and end-to-end planning. Repo under Apache 2.0💙
👉Review https://lnkd.in/p/eezZrSJE
👉Paper https://arxiv.org/pdf/2609.04348
👉Project https://tj12342.github.io/object-concepts-from-motion/
👉Repo https://github.com/TJ12342/object-concepts-from-motion/tree/main | 2 364 |
| 7 | +++ Mistral raises 3B € +++
👉Discussion: https://lnkd.in/p/eVpF--VW | 2 133 |
| 8 | 🪣Weather-Conditioned Depth Anything🪣
👉Weather-Conditioned Depth Anything from Texas A&M is the new SOTA in weather-robust depth estimation. A curated mix of real and synthetic degradation datasets to extract content-independent, degradation-aware weather embeddings. Repo under Apache💙
👉Review https://lnkd.in/p/eW-dsepD
👉Paper https://lnkd.in/er_MvVft
👉Project https://lnkd.in/ehXPs3C7
👉Repo https://lnkd.in/edk7Ts_r | 2 535 |
| 9 | 🍚Vision Weight Estimation🍚
👉Doppio is a novel video dataset capturing video of falling ground coffee, paired with precise, per-frame ground-truth weight measurements: OCR readings are extracted from the display, smoothed and time-lag compensated, and paired with per-frame weight annotations. Repo to be released under Apache💙
👉Review https://www.linkedin.com/posts/visionarynet_computer-vision-weight-estimation-activity-7501900695457951744-ArBO
👉Paper https://lnkd.in/eHuy87SX
👉Project https://lnkd.in/e9g9zeK3
👉Repo https://lnkd.in/emUePTiq | 2 488 |
| 10 | 🦑Unified Segmentation n' Retrieval🦑
👉FoundYou gets an example of your object and it segments the same physical instance in a new image or retrieve it from a large gallery with ONE super-compact model. Repo/demo available💙
👉Review https://lnkd.in/p/ex2qnKHW
👉Paper arxiv.org/pdf/2608.29917
👉Project https://lnkd.in/eNEUB_nV
👉Repo https://lnkd.in/eRyDY6Ue | 3 122 |
| 11 | 🍋🟩Remesh-Aware Mesh Deformation🍋🟩
👉RADmesh is a novel generative deformation technique enhanced by remeshing. Given a text prompt, it deforms and remeshes a mesh region to form new geometric features. Repo MIT💙
👉Review https://lnkd.in/p/eK6FZv9c
👉Paper https://arxiv.org/pdf/2608.17182
👉Project https://threedle.github.io/radmesh/
👉Repo https://github.com/threedle/radmesh/ | 4 618 |
| 12 | 🐆 Anyone in 4D is out 🐆
👉4DAnyone turns a casual monocular video into multi-view videos, enabling downstream 4DGS reconstruction. Full repo under Apache 2.0💙
👉Review https://lnkd.in/p/ec4dzGvb
👉Paper https://arxiv.org/pdf/2608.20335
👉Project https://4danyone.github.io
👉Repo github.com/ant-research/4DAnyone | 3 842 |
| 13 | 🔥🔥UPAL: Unified Points n' Lines🔥🔥
👉ETH (+Microsoft Spatial AI Lab) unveils a novel feature extractor that jointly extracts keypoints, lines, and feature descriptors within a single lightweight net. SOTA in line detection can be achieved by adding only three convolutional layers to existing point extractor. Repo under Apache💙
👉Review https://lnkd.in/p/eW8j5JZj
👉Paper https://arxiv.org/pdf/2608.19894
👉Repo https://github.com/francois141/upal | 4 004 |
| 14 | 🐠Dual-branch Elasticity ID-Tracking🐠
👉TIDE: tracking dense, homogeneous targets, providing a scalable dual-branch design to accommodate diverse hardware constraints. MIT license💙
👉Review https://t.ly/WEDeY
👉Paper https://arxiv.org/pdf/2607.26412
👉Project https://vranlee.github.io/TIDE/
👉Repo https://github.com/vranlee/TIDE | 4 506 |
| 15 | 🔥Decoder-only Any-to-Any Model🔥
👉MODUS unifies any-to-any multimodal generation with one decoder, two experts, and zero task heads. Impressive work. Repo under Apache💙
👉Review https://t.ly/-2QKT
👉Paper https://lnkd.in/dhfBQGhB
👉Project https://lnkd.in/dPD_ECXk
👉Repo https://lnkd.in/dbDHw24u | 4 000 |
| 16 | 🍿 Dawn of Generative Cinematography 🍿
🟩 #TheOdyssey by Christopher Nolan was shot entirely on IMAX 70mm. It feels almost romantic: massive cameras, film stock, premium lenses, and an obsessive pursuit of the highest possible quality at the moment of capture.
👉 Meanwhile, #AI research is heading in the exact opposite direction.
🟩 A pre-print paper released today, "Camera Anything", demonstrates something that sounded like science fiction just a few years ago: you film a scene once... and then you can virtually reposition the camera anywhere.
👉More https://t.ly/Kd7RV
👉Paper arxiv.org/pdf/2607.24591
👉Project yixuanli98.github.io/cameraanything/
👉Repo github.com/yixuanli98/CameraAnything | 3 789 |
| 17 | 🍿Dawn of Generative Cinematography🍿
🟩 The Odissey by Christopher Nolan was shot entirely on IMAX 70mm. It feels almost romantic: massive cameras, film stock, premium lenses, and an obsessive pursuit of the highest possible quality at the moment of capture.
👉 Meanwhile, #AI research is heading in the exact opposite direction.
🟩 A pre-print paper released today, "Camera Anything", demonstrates something that sounded like science fiction just a few years ago: you film a scene once... and then you can virtually reposition the camera anywhere.
🟩 Want a close-up? A drone shot? A ground-level perspective? A side angle? A cinematic tracking shot? You no longer decide where to place the camera during filming. You decide afterwards.
👉 And this fundamentally changes what cinematography means.
🟩 For more than a century, filmmakers have had to make irreversible decisions on set. Camera placement, focal length, movement, framing, etc. These choices became part of the recorded footage forever.
🟩 A scene becomes a 3D representation that can be "re-shot" endlessly from viewpoints that never physically existed. We simply capture "raw" data from which the final result is reconstructed or customized.
🟩Five years from now, will we still talk about shooting a movie? Or will we simply capture a scene and decide later where the camera should have been?
The irony is fascinating. While Nolan reminds us how extraordinary a 70mm camera can be, AI is quietly suggesting that, soon, the camera itself will be optional.
👉The first step towards the generative cinematography.
#deeplearning #computervision #AIwithPapers
👉Discussion https://lnkd.in/dMgakzWm
👉Paper arxiv.org/pdf/2607.24591
👉Project yixuanli98.github.io/cameraanything/
👉Repo github.com/yixuanli98/CameraAnything | 1 |
| 18 | 🍿🍿Dawn of Generative Cinematography🍿🍿
🟩#TheOdyssey by Christopher Nolan was shot entirely on IMAX 70mm. It feels almost romantic: massive cameras, film stock, premium lenses, and an obsessive pursuit of the highest possible quality at the moment of capture.
👉Meanwhile, #AI research is heading in the exact opposite direction.
🟩A pre-print paper released today, "Camera Anything", demonstrates something that sounded like science fiction just a few years ago: you film a scene once... and then you can virtually reposition the camera anywhere.
🟩Want a close-up? A drone shot? A ground-level perspective? A side angle? A cinematic tracking shot? You no longer decide where to place the camera during filming. You decide afterwards.
👉And this fundamentally changes what cinematography means.
🟩For more than a century, filmmakers have had to make irreversible decisions on set. Camera placement, focal length, movement, framing, etc. These choices became part of the recorded footage forever.
🟩A scene becomes a 3D representation that can be "re-shot" endlessly from viewpoints that never physically existed. We simply capture "raw" data from which the final result is reconstructed or customized.
🟩Five years from now, will we still talk about shooting a movie? Or will we simply capture a scene and decide later where the camera should have been?
The irony is fascinating. While Nolan reminds us how extraordinary a 70mm camera can be, AI is quietly suggesting that, soon, the camera itself will be optional.
👉The first step towards the generative cinematography.
#deeplearning #computervision #AIwithPapers
👉Discussion https://lnkd.in/dMgakzWm
👉Paper arxiv.org/pdf/2607.24591
👉Project yixuanli98.github.io/cameraanything/
👉Repo github.com/yixuanli98/CameraAnything | 2 |
| 19 | 🔎MicroZoom at Extreme Scale🔎
👉MicroZoom by UWA synthesizes gigapixel-resolution images grounded in consumer-grade microscope close-ups at magnification levels up to 350×. Impressive. Repo under MIT💙
👉Review https://t.ly/hgJD7
👉Paper https://arxiv.org/pdf/2607.24729
👉Project https://microzoom-sr.github.io/
👉Repo github.com/MicroZoom-SR/MicroZoom-SR.github.io | 2 970 |
| 20 | 💄MagicMakeup Makeup-Transfer💄
👉Makeup-transfer applies the reference makeup to the source face while preserving the source identity. Authors: Zhejiang University & vivo BlueImage Lab. Repo for non commercial💙
👉Review https://t.ly/JYpCr
👉Paper https://arxiv.org/pdf/2607.20924
👉Project https://vivocameraresearch.github.io/magicmakeup/
👉Repo https://github.com/vivoCameraResearch/Magic-Makeup | 2 898 |
