I was talking to Prof. Ramamohan Paturi of UC San Diego yesterday and knew something massive was coming. Phew!

Every automated check passed. The evidence box still missed the bus. We gave Roboflow Agent one minute of drone footage and asked whether an intersection was blocked. The workflow ran, the output parsed, and the structural checks passed—but the box offered as evidence for the blue bus did not contain it. Three checks for your next vision workflow: Does it run? Does it parse? Does the evidence support the answer? Watch the full tutorial: youtu.be/27apodnar2M One feasibility test, not a benchmark or a measure of production accuracy. Footage: Songdo Traffic v2, Robert Fonod, Haechan Cho, Hwasoo Yeo and Nikolas Geroliminis. zenodo.org/records/17924857 — CC BY 4.0: creativecommons.org/licenses…. Resized and compressed; frames extracted and annotated. The dataset authors and Roboflow do not endorse this video. #ComputerVision #Roboflow #AIagents #OpenCV

Same face, different conditions: 0.95 in the studio, 0.78 against a car-video frame. Day, camera and setting changed together—we cannot blame lighting alone. Enroll across days and cameras. Similarity is not accuracy. #OpenCV #ComputerVision Lighting data: Collin Gros (2019), Facial Recognition Dataset VIDEO (part 1 of 2), Mendeley Data V1. doi.org/10.17632/xgg8xcscr5.… — CC BY 4.0 (creativecommons.org/licenses…). Used to derive scores and graphics; no dataset faces shown.

Nobody knows

The astonishing rise of China and the decline of Europe has been a work in progress for years. Yet, it’s unbelievable when you experience it first hand.

Datalab’s Indra OCR runs on CPUs, with no GPU. Its recognizer has about one million parameters. Datalab reports 49 pages/sec on a 32-core server; on 4 cores, about 7 pages/sec. Hardware matters when reading benchmark headlines. In our upside-down scan demo, it rotated the page, detected lines, determined reading order and wrote Markdown in 344 ms on 2 vCPUs. Built for clean printed documents; handwriting, faded scans and complex tables remain limitations. What document type should we test against Tesseract and PaddleOCR next? Sources: datalab.to/blog/indra-ocr github.com/datalab-to/indra Demo page: Attention Is All You Need — Vaswani et al. (2017). #OCR #ComputerVision #DocumentAI #OpenCV #Python

Would I let a video model sign off on completed work? Only after checking how it reached the verdict. Our Nemotron 3.5 Super VL test is a useful example: the robot completed the checklist, but the model could not support one step and still agreed. A correct verdict alone would hide that failure. We also tested a road sign and squat counting. Three case studies—not a benchmark. Human review of references is pending. Full video, “Nemotron 3.5 Super VL Tested: A Correct Answer for the Wrong Reason,” on LearnOpenCV: youtube.com/watch?v=BbRxAsp6… Video sources: NVIDIA; FurnitureBench (CLVR Lab/KAIST); FitnessScape (CC BY 3.0). Full credits in the description. Thumbnail is an illustration. What would you check beyond the final answer? #AI #ComputerVision

I finally watched the movie. The staring is nothing compared to the head-nod that messes your brain. xitter.cf/LearnOpenCV/status/209…

How to create this blue text string: #̢̛ͥ̀̽̽ͨ̌̓͆̇̀̽ͦͨͫͯ̏̎̇̈̚͜҉̕͢͏͡҉̸̶̛͢͡҉̵̨̭̳̘̹̫͔͖̜̠͖̫̲̖̱̤̻̖͉ It’s a # followed by a pile of Unicode combining marks, normally used for accents. They stack above and below the character, spilling into nearby lines. X makes it blue because it recognizes a hashtag. Copy the string to try it.

What interests me about Dream-1 isn't just a new robot demo. It's the possibility of needing less training data every time the hardware changes. Dream Labs trained it on the YAM and showed zero-shot transfer to 27 unseen robots in simulation, plus real arms. I'd want to know where that transfer breaks: unfamiliar workspaces, poor IK, and new gripper designs. Today the scope is bimanual robots with parallel grippers. Selected, sped-up demos aren't a reliability test. I haven't run Dream-1 myself. Footage: Dream Labs (3× simulation, 4× real robots). Research: dreamlabs.ai/research/dream-… AI voice and avatar. What would you test first on your own robot? #Robotics #AI

Tell me you don't know about CUDA (and when it was funded internally at NVIDIA) without telling me you don't know about CUDA.

Is Muse as smart as Dot? I tried this little personal test. A friend's wife invited our family for his birthday party a few days. She had not sent the exact time. I asked both Muse and Dot to check if "Richard Stallman's [not his real name, obviously] wife has sent an exact time for the birthday party" Now, Richard and his wife do not have the same last name. So it requires some reasoning to figure out who I was talking about. Muse said it could not find any communication about Richard's birthday. Dot nailed it. It figured out the relationship, and then informed me that an invitation is waiting for me with the exact time and venue.