AllLLMRoboticsStartupsResearchEthicsBusinessHardwareAutonomousMedicineCreative
Topic hub

AI Image Generators

AI image generators create pictures from a text prompt: Midjourney, Stable Diffusion, FLUX, DALL-E and Nano Banana turn a description into an illustration, photo or artwork in seconds. The quality now rivals professional design work, while courts sort out copyright. Here is all our coverage of image generation: model releases, comparisons, pricing and legal battles.

Official site ↗1162 articles
In the glossary:Text-to-Image ModelDiffusion ModelGenerative AIMultimodal Model
An AI secretary for $77 a month: 88% of answers from DeepSeek, 77% of the budget goes to Opus
LLM·Habr AI

An AI secretary for $77 a month: 88% of answers from DeepSeek, 77% of the budget goes to Opus

Oct 12, 2026·2 min
AI Solved 370 Math Problems, Mathematicians Panic, Musk Seeks $40 Billion: This Week's Highlights
LLM

AI Solved 370 Math Problems, Mathematicians Panic, Musk Seeks $40 Billion: This Week's Highlights

Oct 12, 2026·4 min
Tsinghua Team Pushes Generation Down to a Single Step, From Images to Streaming Video
LLM

Tsinghua Team Pushes Generation Down to a Single Step, From Images to Streaming Video

Oct 12, 2026·2 min
模思智能 Raises Over 1 Billion Yuan in Pre-A for a Real-Time Omni-Modal Model
LLM

模思智能 Raises Over 1 Billion Yuan in Pre-A for a Real-Time Omni-Modal Model

Oct 12, 2026·2 min
New Benchmark Tests Whether AI-Generated Images Obey the Laws of Physics
LLM·Jiqizhixin (机器之心)

New Benchmark Tests Whether AI-Generated Images Obey the Laws of Physics

An image can score high on aesthetics and prompt adherence while showing distorted hands and objects passing through each other. A new test measures "world…

Oct 12, 2026·2 min
UNITAS: A 3D World Model for Robots Claims the Lead on Several Benchmarks
Robotics·Jiqizhixin (机器之心)

UNITAS: A 3D World Model for Robots Claims the Lead on Several Benchmarks

A Chinese team unveiled UNITAS, which it calls the first 3D world model built for robots. It claims the lead on several benchmarks, but the numbers have not been…

Oct 12, 2026·2 min
SAMF Teaches Drones to Locate Themselves on a Satellite Map Using Thermal Imaging, No GNSS Required
Robotics·arXiv cs.CV

SAMF Teaches Drones to Locate Themselves on a Satellite Map Using Thermal Imaging, No GNSS Required

Researchers propose SAMF, a framework that matches drone thermal images to satellite maps using scene structures common to both. The code and the Thermal-UAV-Paired…

Oct 12, 2026·2 min
APEX Compresses Diffusion Latents 128x and Beats a 256-Token Model on ImageNet-512
LLM·arXiv cs.CV

APEX Compresses Diffusion Latents 128x and Beats a 256-Token Model on ImageNet-512

APEX orders latent channels from structure to detail and denoises them asynchronously. On ImageNet-512 it wins at 64x and 128x compression, and the code is already…

Oct 12, 2026·2 min
Top themes
01SWIM saves compute: audio-video generation gains up to 30.7% over Best-of-NOct 12, 2026·2 min02SAM 2.1 fine-tuned on facades and interiors: mIoU rises from 49.9% to 69.6%Oct 12, 2026·2 min03SAIL Keeps Its Target in Frame Using Audio and Text, and Beats Rivals on Two BenchmarksOct 12, 2026·2 min04Researchers Compare CNN, ViT and Mamba Attention Against Human GazeOct 12, 2026·3 min05Stroop Test Shows VLMs Read the Text in an Image Before They See the ColorOct 12, 2026·2 min
ForcingBooster Halves Denoising Steps in Autoregressive Video Generation
LLM·arXiv cs.CV

ForcingBooster Halves Denoising Steps in Autoregressive Video Generation

Oct 12, 2026·2 min
Video-Language Models Confuse Car Maneuvers: LoRA and Probes Fix the Error
LLM·arXiv cs.CV

Video-Language Models Confuse Car Maneuvers: LoRA and Probes Fix the Error

Oct 12, 2026·2 min
MIRAGE anchors video-based 3D reconstruction to LiDAR and beats COLMAP on three datasets
Robotics·arXiv cs.CV

MIRAGE anchors video-based 3D reconstruction to LiDAR and beats COLMAP on three datasets

Oct 12, 2026·2 min
TerraAgent checks whether the AI actually looks at the image: hallucinations drop from 17.1% to 9.8%
LLM·arXiv cs.CV

TerraAgent checks whether the AI actually looks at the image: hallucinations drop from 17.1% to 9.8%

Oct 12, 2026·2 min
AVA improves multimodal ICL accuracy by 1.7 points without any training
LLM·arXiv cs.CV

AVA improves multimodal ICL accuracy by 1.7 points without any training

A preprint proposes AVA, a three-stage pipeline that cleans up the examples in a frozen VLM's prompt. It gains +1.7 points on average across five benchmarks, with…

Oct 12, 2026·2 min
DiffusionART speeds up RL fine-tuning of video models 12x, with no EMA tuning
LLM·arXiv cs.LG

DiffusionART speeds up RL fine-tuning of video models 12x, with no EMA tuning

DiffusionART fine-tunes diffusion models on black-box rewards. On HunyuanVideo-13B it reaches the late-stage reward of DiffusionNFT and Flow-GRPO-Fast in 12x fewer…

Oct 12, 2026·2 min
CacheScope speeds up diffusion models by up to 3.57x and cuts LPIPS by 70%
LLM·arXiv cs.LG

CacheScope speeds up diffusion models by up to 3.57x and cuts LPIPS by 70%

CacheScope needs no fine-tuning. It finds the steps where caching is risky and computes them in full. On FLUX.1-dev, Wan2.1 and Open-Sora 1.2, it gives up to 3.57x speedup and lowers LPIPS to 70.1%.

Oct 12, 2026·2 min
Kairos: a byte-level model for all modalities converges on 440 bytes
LLM·arXiv cs.LG

Kairos: a byte-level model for all modalities converges on 440 bytes

Oct 12, 2026·2 min
GeoSpatialBench Tests MLLMs on 28 Types of Spatial Relations Across Six Cities
LLM·arXiv cs.AI

GeoSpatialBench Tests MLLMs on 28 Types of Spatial Relations Across Six Cities

Oct 12, 2026·2 min
New Method Aligns Encoders With 100–500 Pairs Instead of Millions
LLM·arXiv cs.AI

New Method Aligns Encoders With 100–500 Pairs Instead of Millions

Oct 12, 2026·2 min
arXiv paper finds five flaws in XAI faithfulness metrics
LLM·arXiv cs.AI

arXiv paper finds five flaws in XAI faithfulness metrics

Oct 12, 2026·2 min
Zebra3D speeds up 3D reconstruction by up to 7.1× on 1024 frames without training from scratch
Robotics·arXiv cs.CV

Zebra3D speeds up 3D reconstruction by up to 7.1× on 1024 frames without training from scratch

Oct 12, 2026·2 min
MisVisAgentBench: Misleading Charts Cut Web Agent Success by 34 Percentage Points
LLM

MisVisAgentBench: Misleading Charts Cut Web Agent Success by 34 Percentage Points

Oct 12, 2026·2 min
Linear Head on Qwen3-VL Beats GPT-4o at Scoring Answers Without Human Labels
LLM

Linear Head on Qwen3-VL Beats GPT-4o at Scoring Answers Without Human Labels

Oct 12, 2026·2 min
Runpod shows how to run diffusion models on JAX in GPU pods
LLM

Runpod shows how to run diffusion models on JAX in GPU pods

Oct 12, 2026·2 min
DeepSeek-OCR Compresses Text Context 10x at 97% Accuracy
LLM·YouTube: Two Minute Papers

DeepSeek-OCR Compresses Text Context 10x at 97% Accuracy

DeepSeek proposes storing long text as an image: at 10x compression the model recovers 97% of the content, and at 20x accuracy drops to 60%.

Oct 11, 2026·2 min
BBC: AI Is Devaluing Images and Raising the Price of Human-Made Work
LLM·Hacker News AI

BBC: AI Is Devaluing Images and Raising the Price of Human-Made Work

The cheaper image generation gets, the more authorship is worth. BBC describes a "human premium" on art, and Hacker News collected 78 comments under the piece.

Oct 11, 2026·2 min