Jina AI's jina-ocr-v1 Parses PDF Pages at 2.57 Pages per Second
Jina AI released jina-ocr-v1, a 3.4B mixture-of-experts document parser with speculative decoding that turns pages into Markdown at 2.57 pages per second.
// Intelligence
Image
A focused feed of models, agents, research and open-source releases for people building with AI.
Updated
NVIDIA's Axolotl3D Reconstructs Hidden 3D Geometry From Partial Photos
NVIDIA's Axolotl3D fuses images, camera poses, and partial point clouds into one diffusion pipeline that completes occluded 3D shapes faithfully.
Huawei's Marigold V2 Beats Top Depth Models Training on One 32 GB GPU
Marigold V2 turns Qwen-Image-Edit into a single-step depth, normals, and albedo predictor, fine-tuned on one 32 GB consumer GPU.
Comfy-Org Brings YuE2 Music Generation Natively Into ComfyUI Workflows
Comfy-Org has repackaged the MAP team's YuE2 music model into single-file safetensors, and ComfyUI now ships native nodes to run it.
NVIDIA's HorizonRelight Fixes Flickering Lights in Long AI Videos
NVIDIA and USC present HorizonRelight, a diffusion transformer method that keeps lighting stable across long videos by propagating context between chunks.
Google Pics Brings Nano Banana 2 Into Docs and Slides to Fight Canva
Google Pics packages Nano Banana into a Workspace-native image editor with object-level control, in-image text editing, and live collaboration.
OpenAI's ChatGPT Images 2.5 Cuts Generation Time by 50% and Fixes Edits
OpenAI's new image model brings 50% faster generation, precision comment-based edits, in-chat sketching, and two new API tiers for developers.
Japan's LLM-jp-4-VL 9B Beats InternVL on Japanese While Staying Truly Open Source
Japan's national LLM project releases an Apache-2.0 vision-language model with reasoning traces, trained on a scrubbed 29M-sample dataset.
H-BAC Shrinks a 327 MB Plant Disease Model Down to 6 MB
A unified pruning, quantization and distillation pipeline shrinks a Vision Transformer 54.5x while holding 95.13% accuracy on out-of-distribution chilli disease images.
Ant Group's Ling-3.0-flash-VL Brings Images and Video to Its 124B Open Model
InclusionAI open-sources a 124B-parameter mixture-of-experts vision-language model with 5.5B active parameters, 256K context, and MIT license.
NAVER Labs' BLASt3R Merges Live SLAM and 3D Reconstruction Into One Pipeline
A new hybrid Structure-from-Motion framework from NAVER Labs unifies real-time SLAM and offline reconstruction, beating even calibrated systems while running uncalibrated.
Krea Agents Opens Beta to Replace Node-Wiring With Plain English Prompts
Krea opens the beta for a new agent platform that turns natural-language prompts into finished visual assets, sitting on top of its existing creative suite.
Artificial Analysis Rebuilds Its Image Editing Arena Across 17 Specialized Categories
Artificial Analysis rebuilt its Image Editing Arena with a two-axis taxonomy of editing actions and use cases, revealing which model wins each specific task.
UC Berkeley Team Cuts Diffusion Model Training Time by 40% With Frequency-Aware Loss
A new frequency-domain training objective for pixel-space flow matching cuts convergence time by up to 40% without touching the architecture.
DeepSeek's V4-Flash-Vision-Exp Adds Image Understanding at Half the Cost of Rivals
DeepSeek gives its Flash model eyes with an experimental multimodal release that matches Claude Opus 4.8 on agent tasks at a fraction of the cost.
Peking University's ATGS Reconstructs 1,400-Frame Athletic Scenes in One Shot
A new Gaussian splatting framework reconstructs volumetric videos with thousands of frames of complex motion, extending prior methods by roughly 70x in temporal coverage.
Krea Reveals Krea 3 and an Agent-Driven Creative Platform for Designers
Krea previews a next-generation foundation model with strong editing plus a dedicated agent platform for creative work with MCP and API hooks.
Midjourney's V8.2 Edit Model Merges Inpainting, References and Instructions Into One
Midjourney is testing a V8.2 edit model that handles instruction-based editing, multi-image composition, inpainting, and outpainting in one system.
UNSEEN Gemma 4 Removes AI Refusals With a Single Math Trick
A 26B multimodal Gemma variant with refusal directions surgically removed lands on Hugging Face in GGUF format, ready for llama.cpp.
Google's Planetary Prediction Engine Turns Weeks of Geospatial Work Into Minutes
Google Research unveils an autonomous AI system that turns natural-language questions about food security, disease, and climate risk into trained geospatial models in minutes.
SSMB Learns Blur-Proof Keypoints Without Deblurring or Labeled Data
A new keypoint detector skips deblurring entirely, learning directly from blurred images through self-supervision and beating supervised baselines on matching and localization.
Oxford and MIT Researchers Argue Vision Alone Could Unlock General AI
A group of vision researchers argues that pure vision, not language-tethered multimodal models, could be its own route to general intelligence.
img2threejs Turns Any Photo Into Editable 3D Code With 12k Stars
A new agent skill turns a single reference image into diffable TypeScript that procedurally reconstructs the object as an animation-ready Three.js scene.
Alibaba's Qwen-Image-3.0-Pro Jumps 83 Elo Points but Drops Open Weights
Alibaba's third-generation image model debuts at #6 in editing and #9 in text-to-image, with big Elo jumps and a productivity-first pitch.
No stories match these filters.