Tootfinder

Looks like USPS is rehearsing for the midterms. Thousands of absentee ballots ... where are they? No one knows.
https://www.wtoc.com/2025/10/24/some-chatham-county-voters-may-receive-two-absentee-bal…

Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation
Hongtao Yang, Bineng Zhong, Qihua Liang, Zhiruo Zhu, Yaozong Zheng, Ning Li
https://arxiv.org/abs/2509.19733

Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation
Recently, visual prompt tuning is introduced to RGB-Thermal (RGB-T) tracking as a parameter-efficient finetuning (PEFT) method. However, these PEFT-based RGB-T tracking methods typically rely solely on spatial domain information as prompts for feature extraction. As a result, they often fail to achieve optimal performance by overlooking the crucial role of frequency-domain information in prompt learning. To address this issue, we propose an efficient Visual Fourier Prompt Tracking (named VFPTra…

Developing countries to receive breakthrough HIV prevention drug at low cost
https://www.washingtonblade.com/2025/09/25/developing-countries-to-receive-breakthrough-hiv-prevention-drug-at-low-cost/

Update on the Sony PVM-2530: probably should use RGB before diagnosing color issues (e.g. luma). I did have to get in my custom CMPTR board to do it, but everything lined up perfectly. I do need to fix the geometry a bit, but for right now I think I'll be playing a few games after work.
#electronics

M.2-Adapter quetscht Mini-SSD ins offizielle Raspi-5-Gehäuse
Der M.2 HAT Compact für den Raspberry Pi nimmt 30 mm kleine SSDs huckepack. Das Ganze passt neben den offiziellen CPU-Kühler.
https://www.

Happy birthday Reykjavík! A fun but utterly exhausting day!

ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation
Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme, Daniel Seita
https://arxiv.org/abs/2509.19454 https://…

ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation
Training robust bimanual manipulation policies via imitation learning requires demonstration data with broad coverage over robot poses, contacts, and scene contexts. However, collecting diverse and precise real-world demonstrations is costly and time-consuming, which hinders scalability. Prior works have addressed this with data augmentation, typically for either eye-in-hand (wrist camera) setups with RGB inputs or for generating novel images without paired actions, leaving augmentation for eye…

Next-level recipe: the no recipe recipe. #nommention
https://cooking.nytimes.com/recipes/1023313-bulgogi-style-…

Bulgogi-Style Tofu Recipe (Gift Recipe)
This is a no-recipe recipe, a recipe without an ingredient list or steps. It invites you to improvise in the kitchen. Here's the prompt: bulgogi-style tofu. It’s simple. Press some firm tofu to extract as much liquid as you can. Make a marinade of soy sauce, brown sugar, sesame oil, minced garlic, grated ginger, a spoonful of gochujang, a splash of neutral oil, some sliced scallions and toasted sesame seeds. Slice the tofu into bite-size cubes, and slide them into the marinade. Let that sit …

🐜 Scientists revive old Bulgarian recipe to make yogurt with ants
https://arstechnica.com/science/2025/10/how-ants-can-kick-start-fermentation-to-make-yogurt/

Scientists revive old Bulgarian recipe to make yogurt with ants
Ants carry lactic and acetic acid bacteria that help coagulate milk, as well as formic acid to acidify it.

HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images
Anilkumar Swamy, Vincent Leroy, Philippe Weinzaepfel, Jean-S\'ebastien Franco, Gr\'egory Rogez
https://arxiv.org/abs/2508.16465

HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images
Hand-object 3D reconstruction has become increasingly important for applications in human-robot interaction and immersive AR/VR experiences. A common approach for object-agnostic hand-object reconstruction from RGB sequences involves a two-stage pipeline: hand-object 3D tracking followed by multi-view 3D reconstruction. However, existing methods rely on keypoint detection techniques, such as Structure from Motion (SfM) and hand-keypoint optimization, which struggle with diverse object geometrie…