Goblin
News
AI news by
promptgoblins.ai
|
News
About
News
About
Filtered by:
computer-vision
Clear
Titles
Summaries
April
7
Meta Sapiens2: Human-Centric Vision Models Pretrained on 1B Images
Open Source
1
Apr 29
7
Meta Sapiens2: Human-Centric Vision Models Pretrained on 1B Images
Open Source
· 1 src · Apr 29
Discuss
6
Google Photos to Launch AI-Powered Digital Wardrobe with Virtual Try-On
Products
1
Apr 29
6
Google Photos to Launch AI-Powered Digital Wardrobe with Virtual Try-On
Products
· 1 src · Apr 29
Discuss
7
Vision Banana: Image Generation Pretraining Achieves SOTA on Diverse Vision Tasks
Research
1
Apr 27
7
Vision Banana: Image Generation Pretraining Achieves SOTA on Diverse Vision Tasks
Research
· 1 src · Apr 27
Discuss
6
State of Efficient Video AI in 2026: Encoders, Edge Deployment, Scale Challenges
Research
1
Apr 27
6
State of Efficient Video AI in 2026: Encoders, Edge Deployment, Scale Challenges
Research
· 1 src · Apr 27
Discuss
8
Sony AI Robot Ace Beats Elite Table Tennis Players in Nature-Published Milestone
Updated
Research
3
May 4
8
Sony AI Robot Ace Beats Elite Table Tennis Players in Nature-Published Milestone
Top
Research
· 3 srcs · May 4
Discuss
7
Google Launches Generative AI Features for Enterprise Geospatial Analysis
Enterprise
1
Apr 22
7
Google Launches Generative AI Features for Enterprise Geospatial Analysis
Enterprise
· 1 src · Apr 22
Discuss
7
FlashDrive: 4.5x Latency Reduction for Reasoning VLA Autonomous Driving Models
Research
1
Apr 21
7
FlashDrive: 4.5x Latency Reduction for Reasoning VLA Autonomous Driving Models
Research
· 1 src · Apr 21
Discuss
7
Amazon Nova Multimodal Embeddings Enables Native Video Semantic Search
Products
2
Apr 17
7
Amazon Nova Multimodal Embeddings Enables Native Video Semantic Search
Products
· 2 srcs · Apr 17
Discuss
6
NVIDIA Releases Nemotron OCR v2: Multilingual Accuracy via 12M Synthetic Images
Models
1
Apr 17
6
NVIDIA Releases Nemotron OCR v2: Multilingual Accuracy via 12M Synthetic Images
Models
· 1 src · Apr 17
Discuss
7
Lyra 2.0: NVIDIA Framework for Explorable Generative 3D Worlds
Research
1
Apr 16
7
Lyra 2.0: NVIDIA Framework for Explorable Generative 3D Worlds
Research
· 1 src · Apr 16
Discuss
7
Elastic Looped Transformers Achieve 4x Parameter Reduction for Visual Generation
Research
1
Apr 14
7
Elastic Looped Transformers Achieve 4x Parameter Reduction for Visual Generation
Research
· 1 src · Apr 14
Discuss
7
Researchers Reverse-Engineer Google's SynthID Watermark, Achieve 91% Bypass Effectiveness
Security
1
Apr 10
7
Researchers Reverse-Engineer Google's SynthID Watermark, Achieve 91% Bypass Effectiveness
Security
· 1 src · Apr 10
Discuss
7
Process-Driven Image Generation Introduces Multi-Step Reasoning for Visual Synthesis
Research
1
Apr 10
7
Process-Driven Image Generation Introduces Multi-Step Reasoning for Visual Synthesis
Research
· 1 src · Apr 10
Discuss
7
Tesla FSD v14.3: Fleet Learning, MLIR Compiler Rewrite, 20% Faster Reactions
Products
1
Apr 8
7
Tesla FSD v14.3: Fleet Learning, MLIR Compiler Rewrite, 20% Faster Reactions
Products
· 1 src · Apr 8
Discuss
7
Netflix & INSAIT Release VOID: AI Video Inpainting That Removes Objects and Their Physical Interactions
Research
1
Apr 6
7
Netflix & INSAIT Release VOID: AI Video Inpainting That Removes Objects and Their Physical Interactions
Research
· 1 src · Apr 6
Discuss
7
Spain's Xoople Raises $130M Series B to Build AI-Focused Satellite Constellation
Markets
1
Apr 6
7
Spain's Xoople Raises $130M Series B to Build AI-Focused Satellite Constellation
Markets
· 1 src · Apr 6
Discuss
6
TGS and AWS Cut Seismic Foundation Model Training from 6 Months to 5 Days
Enterprise
1
Apr 6
6
TGS and AWS Cut Seismic Foundation Model Training from 6 Months to 5 Days
Enterprise
· 1 src · Apr 6
Discuss
8
NYC Hospital CEO Wants AI to Replace Radiologists; Stanford Study Flags "Mirage" Risk
Safety
1
Apr 4
8
NYC Hospital CEO Wants AI to Replace Radiologists; Stanford Study Flags "Mirage" Risk
Top
Safety
· 1 src · Apr 4
Discuss
7
HCompany Launches HoloTab Browser Extension Powered by Holo3 Model
Updated
Products
2
Apr 15
7
HCompany Launches HoloTab Browser Extension Powered by Holo3 Model
Products
· 2 srcs · Apr 15
Discuss
6
MLB's AI Strike Zone System Dominates Early 2026 Season
Enterprise
1
Apr 3
6
MLB's AI Strike Zone System Dominates Early 2026 Season
Enterprise
· 1 src · Apr 3
Discuss
6
Falcon Perception: 0.6B Early-Fusion Model for Open-Vocabulary Grounding and Segmentation
Models
1
Apr 3
6
Falcon Perception: 0.6B Early-Fusion Model for Open-Vocabulary Grounding and Segmentation
Models
· 1 src · Apr 3
Discuss
6
Ray-Ban Meta: Prescription Frames and New AI Features
Updated
Products
2
Apr 6
6
Ray-Ban Meta: Prescription Frames and New AI Features
Products
· 2 srcs · Apr 6
Discuss
6
CHMv2: AI-Powered Global Canopy Height Map Advances Forest Carbon Monitoring
Research
1
Apr 3
6
CHMv2: AI-Powered Global Canopy Height Map Advances Forest Carbon Monitoring
Research
· 1 src · Apr 3
Discuss
6
Google Creates High-Resolution Satellite Imagery Map of Brazil's Forests
Products
1
Apr 3
6
Google Creates High-Resolution Satellite Imagery Map of Brazil's Forests
Products
· 1 src · Apr 3
Discuss
6
IBM Granite 4.0 3B Vision: Compact Multimodal Model for Enterprise Document AI
Models
1
Apr 3
6
IBM Granite 4.0 3B Vision: Compact Multimodal Model for Enterprise Document AI
Models
· 1 src · Apr 3
Discuss
Last Week
7
Fei-Fei Li's World Labs Raises $1B+ to Build Spatial Intelligence AI
Products
1
Jun 15
7
Fei-Fei Li's World Labs Raises $1B+ to Build Spatial Intelligence AI
Products
· 1 src · Jun 15
Discuss
2 Weeks Ago
7
Decart Launches Oasis 3 World Model for Photorealistic Autonomous Vehicle Simulation via API
Products
1
Jun 10
7
Decart Launches Oasis 3 World Model for Photorealistic Autonomous Vehicle Simulation via API
Products
· 1 src · Jun 10
Discuss
3 Weeks Ago
6
Amazon Ring Faces Class Action Over Familiar Faces AI Facial Recognition Feature
Security
1
Jun 2
6
Amazon Ring Faces Class Action Over Familiar Faces AI Facial Recognition Feature
Security
· 1 src · Jun 2
Discuss
Last Month
7
NVIDIA LocateAnything: Parallel Box Decoding Breaks VLM Grounding Speed-Accuracy Tradeoff
Research
1
May 28
7
NVIDIA LocateAnything: Parallel Box Decoding Breaks VLM Grounding Speed-Accuracy Tradeoff
Research
· 1 src · May 28
Discuss
7
Trajectory: Ex-Google DeepMind and Apple Researchers Target Visual AI with $50M Seed
Markets
1
May 28
7
Trajectory: Ex-Google DeepMind and Apple Researchers Target Visual AI with $50M Seed
Markets
· 1 src · May 28
Discuss
7
MAI-Image-2.5 Launches at No. 3 on Arena Text-to-Image Leaderboard
Models
1
May 27
7
MAI-Image-2.5 Launches at No. 3 on Arena Text-to-Image Leaderboard
Models
· 1 src · May 27
Discuss
7
LiteFrame Cuts Video LLM Inference Latency 35% with Compact Encoder
Research
1
May 21
7
LiteFrame Cuts Video LLM Inference Latency 35% with Compact Encoder
Research
· 1 src · May 21
Discuss
8
Ukraine Drones Reportedly Using AI Facial Recognition to Target Soldiers
Security
1
May 19
8
Ukraine Drones Reportedly Using AI Facial Recognition to Target Soldiers
Top
Security
· 1 src · May 19
Discuss
8
Microsoft Open-Sources TRELLIS.2: 4B-Parameter Image-to-3D Model with Novel Voxel Representation
Open Source
1
May 19
8
Microsoft Open-Sources TRELLIS.2: 4B-Parameter Image-to-3D Model with Novel Voxel Representation
Top
Open Source
· 1 src · May 19
Discuss
8
Google Genie World Model Gains Street View Integration for Real-World Simulation
Models
1
May 19
8
Google Genie World Model Gains Street View Integration for Real-World Simulation
Models
· 1 src · May 19
Discuss
8
Alibaba Qwen Releases Wave: Open MoE, Image Gen, and Compact Vision Models
Models
1
May 19
8
Alibaba Qwen Releases Wave: Open MoE, Image Gen, and Compact Vision Models
Top
Models
· 1 src · May 19
Discuss
6
OlmoEarth v1.1: 3x Compute Reduction for Satellite Imagery AI
Models
1
May 19
6
OlmoEarth v1.1: 3x Compute Reduction for Satellite Imagery AI
Models
· 1 src · May 19
Discuss
6
PaddleOCR 3.5 Adds Transformers Backend for OCR and Document Parsing
Open Source
1
May 18
6
PaddleOCR 3.5 Adds Transformers Backend for OCR and Document Parsing
Open Source
· 1 src · May 18
Discuss
6
NVIDIA SANA-WM: 2.6B-Parameter Open-Source World Model with 720p Video and 6-DoF Camera Control
Models
1
May 18
6
NVIDIA SANA-WM: 2.6B-Parameter Open-Source World Model with 720p Video and 6-DoF Camera Control
Models
· 1 src · May 18
Discuss
8
Meta Launches Muse Spark: New Foundational Model Powering Meta AI Across Apps and Glasses
Models
1
May 13
8
Meta Launches Muse Spark: New Foundational Model Powering Meta AI Across Apps and Glasses
Models
· 1 src · May 13
Discuss
7
Alibaba Releases Qwen-Image-2.0: Unified Image Generation and Editing Model
Models
1
May 13
7
Alibaba Releases Qwen-Image-2.0: Unified Image Generation and Editing Model
Models
· 1 src · May 13
Discuss
7
Perceptron Mk1: Video Analysis AI Model Priced 80-90% Below Frontier Rivals
Models
1
May 13
7
Perceptron Mk1: Video Analysis AI Model Priced 80-90% Below Frontier Rivals
Models
· 1 src · May 13
Discuss
7
A²RD: Agentic Diffusion Architecture Achieves 30% Consistency Gains in Long-Form Video Generation
Research
1
May 12
7
A²RD: Agentic Diffusion Architecture Achieves 30% Consistency Gains in Long-Form Video Generation
Research
· 1 src · May 12
Discuss
6
Tesla Vision Deploys Airbags Up to 70ms Earlier Using Camera-Based Crash Prediction
Products
1
May 11
6
Tesla Vision Deploys Airbags Up to 70ms Earlier Using Camera-Based Crash Prediction
Products
· 1 src · May 11
Discuss
8
Meta Deploys AI to Detect Underage Users via Height and Bone Structure Analysis
Products
1
May 5
8
Meta Deploys AI to Detect Underage Users via Height and Bone Structure Analysis
Top
Products
· 1 src · May 5
Discuss
6
End-to-End Autoregressive Image Generation Achieves FID 1.48 on ImageNet
Research
1
May 5
6
End-to-End Autoregressive Image Generation Achieves FID 1.48 on ImageNet
Research
· 1 src · May 5
Discuss
8
Inside Israel's AI Targeting System: How Phone Data Becomes a Death Sentence
Security
1
May 4
8
Inside Israel's AI Targeting System: How Phone Data Becomes a Death Sentence
Top
Security
· 1 src · May 4
Discuss
6
Edit-R1: Verifier-Based Reinforcement Learning Framework Advances Image Editing
Research
1
May 4
6
Edit-R1: Verifier-Based Reinforcement Learning Framework Advances Image Editing
Research
· 1 src · May 4
Discuss
8
Mayo Clinic AI Detects Pancreatic Cancer Signs Up to 3 Years Before Diagnosis
Research
1
May 2
8
Mayo Clinic AI Detects Pancreatic Cancer Signs Up to 3 Years Before Diagnosis
Research
· 1 src · May 2
Discuss
6
GLM-5V-Turbo: Multimodal-Native Foundation Model for Agentic AI
Models
1
May 1
6
GLM-5V-Turbo: Multimodal-Native Foundation Model for Agentic AI
Models
· 1 src · May 1
Discuss
Filters
Signal
Title
Category
Sources
Posted
Discuss
