¡Ya disponible! Investigación de Telegram 2025 — los principales insights del año 
AI with Papers - Artificial Intelligence & Deep Learning
Ir al canal en 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
Mostrar más📈 Análisis del canal de Telegram AI with Papers - Artificial Intelligence & Deep Learning
El canal AI with Papers - Artificial Intelligence & Deep Learning (@ai_deeplearning) en el segmento lingüístico de Inglés es un actor destacado. Actualmente la comunidad reúne a 17 116 suscriptores, ocupando la posición 7 702 en la categoría Tecnologías y Aplicaciones y el puesto 2 213 en la región Malasia.
📊 Métricas de audiencia y dinámica
Desde su creación el невідомо, el proyecto ha mostrado un crecimiento acelerado, reuniendo a 17 116 suscriptores.
Según los últimos datos del 30 junio, 2026, el canal mantiene una actividad estable. En los últimos 30 días la variación de miembros fue de -151, y en las últimas 24 horas de -5, conservando un alto alcance.
- Estado de verificación: No verificado
- Tasa de interacción (ER): El promedio de interacción de la audiencia es 19.20%. Durante las primeras 24 horas tras publicar, el contenido suele obtener N/A% de reacciones respecto al total de suscriptores.
- Alcance de las publicaciones: Cada publicación recibe en promedio 3 286 visualizaciones. En el primer día suele acumular 0 visualizaciones.
- Reacciones e interacción: La audiencia responde de forma activa: el promedio de reacciones por publicación es 16.
- Intereses temáticos: El contenido se centra en temas clave como framework, object, dataset, tba, depth.
📝 Descripción y política de contenido
El autor describe el recurso como un espacio para expresar opiniones subjetivas:
“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”
Gracias a la alta frecuencia de actualizaciones (últimos datos recibidos el 01 julio, 2026), el canal mantiene la vigencia y un amplio alcance. La analítica demuestra que la audiencia interactúa activamente con el contenido, lo que lo convierte en un punto de referencia dentro de la categoría Tecnologías y Aplicaciones.
17 116
Suscriptores
-524 horas
-307 días
-15130 días
Archivo de publicaciones
🍜 SURF-GAN: NeRF - >StyleGAN 🍜
👉 Editable portraits by injecting the NeRF's prior into StyleGAN
😎Review https://bit.ly/3SohEw3
😎Project jgkwak95.github.io/surfgan
😎Paper arxiv.org/pdf/2207.10257.pdf
😎Code github.com/jgkwak95/SURF-GAN
🥶 Lumos by #Nvidia: Relighting Portrait 🥶
👉The new SOTA in relighting without requiring a light stage
😎Review https://bit.ly/3dCH9ej
😎Project deepimagination.cc/Lumos
😎Paper arxiv.org/pdf/2209.10510.pdf
😎Demo http://imaginaire.cc/Lumos/
🚜 NeRF-Factory: a NeRF collection 🚜
👉PyTorch-reimplemented NeRF library with 7 popular models/implementations & 7 datasets
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅NeRF: Project | Paper | Code
✅NeRF++: Paper | Code
✅DVGO: Project | Paper v1/v2 | Code
✅Plenoxels: Project | Paper | Code
✅Mip-NeRF: Project | Paper | Code
✅Mip-NeRF360: Project | Paper | Code
✅Ref-NeRF: Project | Paper | Code
More: https://bit.ly/3qUgmgC
🦪StereoVoxelNet: RT Obstacles Detection🦪
👉Novel deep neural approach to detect occupancy from stereo images directly
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Occupancy voxels via deep learning
✅RT on Jetson-TX2 (-98% CPU of SOTA)
✅Optimization via octrees / sparse conv.
✅Real-world stereo in/outdoor dataset
More: https://bit.ly/3BylAn3
🍈SegNeXt: new SOTA in Semantic Seg.🍈
👉SOTA (by large margin) on ADE20K, Cityscapes, COCO-Stuff, Pascal VOC, Pascal Context, and iSAID 🤯
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Novel tailored network architecture
✅Spatial attention via multi-scale feats
✅Encoder + conv. better than transformers
✅SOTA on several datasets (ADE20K, etc.)
More: https://bit.ly/3UrZhrH
🍋YOLOPv2: Better Driving Perception🍋
👉YOLOPv2: simultaneous object, road segmentation & lane detection
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅E2E perception net with better backbone
✅Efficient ELAN for reasonable memory
✅Stability for adapting to scenarios
✅SOTA on BDD100K, +50% faster!
✅Source code under MIT license
More: https://bit.ly/3LvYGBh
🐸 CHARL-E: Stable Diffusion in 1 click 🐸
👉CHARL-E packages Stable Diffusion into a simple app.
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅No setup, dependencies, or internet
✅Images with 1-click on #macbook
✅Suitable only for M1/M2 processor
✅Source code under MIT license
More: https://bit.ly/3xv2z3G
🍐PeRFception: Largest IR Dataset🍐
👉#Nvidia, a new frontier in data collection via Plenoxels: same info, -96.4% in size.
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅POSTECH + NVIDIA + Caltech = 🤯
✅Size: -96.4% from original dataset!
✅2D/3D image/object class/semantic
✅Ready-to-use pipeline for implicit dataset
More: https://bit.ly/3eW9hJA
🟨 Lang<->Pics in 100+ Languages 🟨
👉#Google PaLI: unified lang-image #AI to perform tasks in 109 languages 🤯
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅PaLI: Pathways Lang & Image model
✅Answering, captioning, reasoning, etc
✅From Eng. to 109 lang. understanding
✅The new SOTA on several datasets
More: https://bit.ly/3QMslHC
🈯SAMURAI: in-the-wild Shape/Material🈯
👉#Google SAMURAI: shape, BRDF, per-image pose & illumination. Relightable #3D assets for #AR/#VR.
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Parametrization for varying distances
✅Camera multiplex optimization
✅Posterior scaling of input images
✅Explicit meshes extraction with BRDF
✅Code/data soon available ->#NeurIPS
More: https://bit.ly/3BKWgf3
🉐#AI finds where IG photos are taken🉐
👉Brilliant work of Depoorter, Belgium artist that handles #privacy, #AI & #socialmedia
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Recorded open cameras for weeks
✅Scraped all #Instagram photos
✅Matching Instagram vs. footage
More: https://bit.ly/3eL5dfc
🔥🔥 UPDATE 🔥🔥
Code Released: https://github.com/sczhou/CodeFormer
🔥 A Survey on Diffusion Models 🔥
👉A comprehensive review of denoising diffusion models in #computervision 🤯
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Overview on diffusion models
✅Hot trend for the generative AI
✅A multi-perspective categorization
✅Current limitations / new directions
More: https://bit.ly/3RYG5zP
💮MAXIM: Multi-Axis MLP for Vision💮
👉#Google opens MAXIM, a multi-axis MLP for low-level vision
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Denoising, deblurring, dehazing, etc
✅Multi-axis gated MLP, linear complexity
✅Cross gating block, separate features
✅SOTA results on several datasets!
More: https://bit.ly/3Dmp8LI
🏵️ TORAS: SOTA #AI for annotation 🏵️
👉TORAS: web-based AI-powered, cooperative, annotation platform.
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅SOTA AI tools -> significant speedup
✅"Recipes" to define how to annotate
✅Repo with folder structure for storage
✅Also on-prem for (commercial) firms
More: https://bit.ly/3L78YI2
💜 #Selfdriving in 80's. Damn Romantic 💜
👉The first self-driving car with people on board, 1986. So slow and lovely.
More: https://bit.ly/3BtRDon
🥤K-VIL: Keypoint-based visual imitation🥤
👉K-VIL: auto-incremental extraction of object-centric task representation.
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Efficient task-relevant keypoints
✅Embodiment-independent tasks
✅Adaptation of tasks to new scenes
✅Input: only a small set of demo clips
✅Novel keypoint-based controller
More: https://bit.ly/3eIrxpP
🐲 Open-Source Self-Driving projects 🐲
👉A free repo with many autonomous vehicle-related projects
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Basic/Advance Lane/Line Detection
✅Driving behavior by training & validating
✅Autopilot: predicting steering angle
More: https://bit.ly/3qqJ7RB
🎪 SOTA in Arbitrary Shape Text Detection 🎪
👉Novel unified coarse-to-fine Transformer for arbitrary shape text detection
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Coarse-to-fine arbitrary text detection
✅Accurate text detection, NO post-process
✅Boundary proposal generation mechanism
✅Innovative boundary transformer (iterative)
✅Boundary energy loss (BEL) for refinement
More: https://bit.ly/3D6Ryt4
👹TT-GNeRF: generative NeRF for Faces👹
👉TT-GNeRF: a novel 3D-aware GANs based on generative NeRF for faces
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅ETH + Uni_Trento + #Snap 🤯
✅DAEM for disentanglement of 3D model
✅"Training-as-Init, Optimizing-for-Tuning"
✅Consistency++, preserving non-target ROI
✅Unsupervised optimization of geometry
More: https://bit.ly/3ARZmMw
