现已上线！2025 年 Telegram 研究 — 年度关键洞察 
AI with Papers - Artificial Intelligence & Deep Learning
前往频道在 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
显示更多📈 Telegram 频道 AI with Papers - Artificial Intelligence & Deep Learning 的分析概览
频道 AI with Papers - Artificial Intelligence & Deep Learning (@ai_deeplearning) 英语 语言赛道中的 是活跃参与者。目前社区聚集了 17 173 名订阅者，在 技术与应用 类别中位列第 7 725，并在 马来西亚 地区排名第 2 238 位。
📊 受众指标与增长动态
自 невідомо 创建以来，项目保持高速增长，吸引了 17 173 名订阅者。
根据 19 六月, 2026 的最新数据，频道保持稳定运转。过去 30 天订阅人数变化为 -177，过去 24 小时变化为 -9，整体触达仍然可观。
- 认证状态： 未认证
- 互动率 (ER)： 平均受众互动率为 21.83%。内容发布后 24 小时内通常能获得 N/A% 的反应，占订阅者总量。
- 帖子覆盖： 每篇帖子平均可获得 3 749 次浏览，首日通常累积 0 次浏览。
- 互动与反馈： 受众积极参与，单帖平均反应数为 26。
- 主题关注点： 内容集中在 framework, object, dataset, tba, depth 等核心主题上。
📝 描述与内容策略
作者将该频道定位为表达主观观点的平台：
“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”
凭借高频更新（最新数据采集于 20 六月, 2026），频道始终保持新鲜度与高覆盖。分析显示受众积极互动，使其成为 技术与应用 类别中的关键影响点。
17 173
订阅者
-924 小时
-397 天
-17730 天
帖子存档
💜MoRo: Human Motion Recovery💜
👉Masked modeling for human motion Recovery under Occlusions. Given a monocular video captured from a static camera, MoRo (by ETHZ & #Meta) robustly reconstructs accurate/physically plausible human motion, even under challenging occlusions. Repo released💙
👉Review https://t.ly/kK_je
👉Paper arxiv.org/pdf/2601.16079
👉Project mikeqzy.github.io/MoRo/
👉Repo github.com/mikeqzy/MoRo
🦧VideoMaMa: Mask-Guided Matting🦧
👉VideoMaMa is novel a diffusion-based model that converts binary segmentation masks into continuous alpha mattes. Repo, Dataset & Demo💙
👉Review https://t.ly/l_0f8
👉Paper arxiv.org/pdf/2601.14255
👉Project cvlab-kaist.github.io/VideoMaMa
👉Repo github.com/cvlab-kaist/VideoMaMa
👉Demo huggingface.co/spaces/SammyLim/VideoMaMa
💊Foundation Medical SAM3 💊
👉Medical SAM3: foundation model for universal prompt-driven medical image segmentation, by fully fine-tuning SAM3 on large-scale, heterogeneous 2D/3D medical imaging datasets with paired segmentation masks-text prompts. Repo & Demo announced💙
👉Review https://t.ly/C6jcy
👉Paper https://arxiv.org/pdf/2601.10880
👉Project chongcongjiang.github.io/MedicalSAM3/#
👉Repo github.com/AIM-Research-Lab/Medical-SAM3
💚 #META 3D Casual Captures 💚
👉#META unveils ShapeR, a novel approach for conditional 3D object shape generation from casually captured sequences. Impressive results. Repo under CC BY-NC 4.0💙
👉Review https://t.ly/j08sJ
👉Paper arxiv.org/pdf/2601.11514
👉Project facebookresearch.github.io/ShapeR/
👉Repo github.com/facebookresearch/ShapeR
👹SOTA Part-level Generator👹
👉A novel a text-to-motion model that learns to compose complex motions through hierarchical conditioning on part-, action- & sequence-level text, enabling fine-grained control over body parts & timing. Code, models & Dataset to be released💙
👉Review https://t.ly/leB_R
👉Paper arxiv.org/pdf/2601.10909
👉Project coral79.github.io/frankenmotion/
👉Repo github.com/Coral79/FrankenMotion-Code
💢3D Human Gen-Seg💢
👉CoMoVi takes an input image with a text description and generates 3D human motion & video sequence synchronously within a single diffusion denoising loop. Repo & Dataset releasing💙
👉Review https://t.ly/khSkm
👉Paper arxiv.org/pdf/2601.10632
👉Project igl-hkust.github.io/CoMoVi/
👉Repo github.com/IGL-HKUST/CoMoVi
👉Data huggingface.co/datasets/AfterJourney/CoMoVi-Dataset
💜Interactive Humanoid Generation💜
👉FlowAct-R1 by ByteDance is a novel framework that enables lifelike, responsive, and high-fidelity humanoid video generation for seamless real-time interaction. No code but impressive results (see video with audio) 💙
👉Review https://t.ly/aQhol
👉Paper arxiv.org/pdf/2601.10103
👉Project grisoon.github.io/FlowAct-R1/
🍿100M Video Action Dataset🍿
👉Action100M by META is a large-scale dataset w/ 1.2M instructional videos (14.6 years of duration), yielding O(100M) temporally localized segments with open-vocabulary action supervision and rich captions. Repo under FAIR NC Research License💙
👉Review https://t.ly/w5KXe
👉Paper https://arxiv.org/pdf/2601.10592
👉Repo https://github.com/facebookresearch/Action100M
🎇 Multi-target SAM3 🎇
👉SAM3-DMS is a novel training-free decoupled strategy that utilizes fine-grained memory selection on individual objects. Robust identity preservation and tracking stability. Repo under SAM License💙
👉Review https://t.ly/jJOAr
👉Paper https://arxiv.org/pdf/2601.09699
👉Repo https://github.com/FudanCVL/SAM3-DMS
💚 Segment Anything w/ Geometry💚
👉3AM (NYCU + #Nvidia) offers cross-view correspondence even under large viewpoint changes, cluttered scenes, and variations in capture conditions, enabling robust object tracking from both videos & casual multi-view images. Repo (coming) & Demo available💙
👉Review https://t.ly/olZwE
👉Paper https://arxiv.org/pdf/2601.08831
👉Project https://jayisaking.github.io/3AM-Page/
👉Repo https://github.com/jayisaking
👉Demo https://huggingface.co/spaces/nycu-cplab/3AM
👉Games Workshop (Warhammer) is banning the use of AI in creative and design processes to protect IP and human creativity. A decision that goes against the current hype of widespread AI adoption.
And what about your organization? I need your help👇
Vote: https://www.linkedin.com/posts/visionarynet_ai-activity-7417106327019196417-TpGL
In 2026, who should we keep an eye on?
Vote: https://www.linkedin.com/posts/visionarynet_ai-deeplearning-aiwithpapers-activity-7416886610795077632-qQeP/
🫛Active Object Reconstruction🫛
👉ObjSplat (Beijing) autonomously plans viewpoints and progressively reconstructs an unknown object into a Hi-Fi Gaussian model and water-tight mesh, enabling direct use in physics simulations. Repo announced💙
👉Review https://t.ly/au6HE
👉Paper arxiv.org/pdf/2601.06997
👉Project li-yuetao.github.io/ObjSplat-page/
👉Repo https://github.com/Li-Yuetao/ObjSplat
🔥Orient Anything V2 is out🔥
👉Orient Anything V2 is a foundation model for unified understanding of object 3D orientation and rotation from single or paired images. Repo under CC-BY-4.0💙
👉Review https://t.ly/Ht7Xd
👉Paper arxiv.org/pdf/2601.05573
👉Project orient-anythingv2.github.io/
👉Repo github.com/SpatialVision/Orient-Anything-V2
🔥 New #AI Startups in 2026? 🔥
In 2026, which area would you focus on?
🤖Agents → workflows, copilots, etc.
🏭Vertical AI → Pharma, Automotive, Energy ...
🧠Infrastructure → MLOps, Security, Cost Control ...
🎨AI for Creators/Media → Video, avatars, contents ...
Please, help me understanding what's next with this poll on LinkedIn :)
https://www.linkedin.com/posts/visionarynet_ai-ai-deeplearning-activity-7415377341779996672-sQO1
LUV U \m/
🌍Label Any Object in 3D 🌍
👉LabelAny3D: novel analysis-by-synthesis framework that reconstructs holistic 3D scenes from 2D to efficiently produce HQ 3D BBs annotations. Repo under CC-BY-4.0 license💙
👉Review https://t.ly/bO93j
👉Paper https://lnkd.in/dYb97zWG
👉Project https://lnkd.in/dJ9UKERb
👉Repo https://lnkd.in/d9SxtmiA
🦙 Depth as Neural Implicit 🦙
👉InfiniDepth represents depth as neural implicit fields, "infinite" (i.e.16K) resolution and geometrical details. Repo under Apache 2.0💙
👉Review https://t.ly/4we5t
👉Paper https://lnkd.in/dpiHQExj
👉Project https://lnkd.in/dy3JxKye
👉Repo https://lnkd.in/dAXbnK5z
⭐ TOP 5 Papers you loved in 2025 ⭐
👉 In 2025 novel architectures have redefined efficiency and accuracy, and almost every day brought a new SOTA in image understanding, tracking, and #GenAI. It’s been an inspiring ride, and 2026 it will be even wilder. This community (LinkedIn + Telegram) is now around 80,000+ people.
𝐏𝐚𝐩𝐞𝐫𝐬 (𝐛𝐲 𝐲𝐨𝐮𝐫 𝐩𝐫𝐞𝐟𝐞𝐫𝐞𝐧𝐜𝐞):
⭐3D LLM Understanding https://t.ly/ejr1s
⭐DynOMo is out https://t.ly/t5pCf
⭐Tracking Transformations https://t.ly/NPyW4
⭐YOLOv12 (new SOTA) https://t.ly/jj1oR
⭐Gaussian Surface Tracking https://t.ly/udpMq
Thank you all💙
