darshan retweeted
the full geometric deep learning book draft is now complete.
all chapters available online on our website (link in thread).
🫡
@mmbronstein @TacoCohen
darshan retweeted
We’re presenting VisionSIM as a spotlight at @corl_conf #CoRL2026!
VisionSIM is a Blender-based multi-sensor simulator for RGB, thermal, event cameras & more—with realistic sensor effects and pixel-perfect ground truth.
Paper + code: wision-lab.github.io/visions…
🧵 1/n
darshan retweeted
Introducing Lattice, a local LaTeX workspace for your research.
A paper is more than a .tex file: the papers you cite, notes, slides, Overleaf co-authors and now an AI agent.
I wanted it all in one app, so I built it.
Free to download, open source:
leo1oel.github.io/lattice
darshan retweeted
📢📢📢 Introducing 𝐒𝐨𝐥𝐯𝟑𝐑
Can geometric foundation models move beyond fixed-set prediction and keep solving like classical SfM?
We turn a looped Transformer into a reusable 𝐥𝐞𝐚𝐫𝐧𝐞𝐝 𝐠𝐞𝐨𝐦𝐞𝐭𝐫𝐢𝐜 𝐬𝐨𝐥𝐯𝐞𝐫
🌐 Project: ubc-vision.github.io/solv3r
🧵👇
darshan retweeted
so this is how you unite this country
cricket 07 with an online multiplayer mode. play with your friends
all you need is a web browser
link: cricket07.dhaiwat.com
darshan retweeted
Introducing terrio: geospatial data I/O in pure Rust!
terrio reads, writes, converts and reprojects geospatial rasters, vector data and point clouds, with no C dependencies. No GDAL or PROJ to install, nothing to compile: it builds anywhere Rust does, including WebAssembly, so the same engine runs on the command line, in Python, and in your web browser.
What it does
- Rasters: GeoTIFF and COG, Zarr and GeoZarr, netCDF, HDF5, PMTiles, MBTiles and more, read in place from the cloud, so only the bytes needed are fetched.
- Vectors: GeoPackage, Shapefile, GeoJSON, FlatGeobuf, GeoParquet, OpenStreetMap PBF and vector tiles, with filters, field selection and reprojection.
- Point clouds: LAS, LAZ, COPC, EPT, PLY and E57, with PDAL-style filters (ground classification, noise, heights above ground) and gridding into DSMs and DTMs. Files larger than memory are converted in chunks.
- GDAL-style processing: translate, warp, mosaic, rasterize, polygonize, terrain analysis, raster calculator, proximity and sieve.
- Remote data: http(s), S3, Google Cloud Storage, Azure, zip archives and STAC searches as inputs.
- Accurate: coordinate transformations agree with GDAL's within a centimetre for all 6,354 EPSG CRSs GDAL transforms, and outputs are tested against GDAL on real-world data.
- Fast: in our benchmarks, warping, mosaicking and writing COGs run several times faster than the GDAL utilities.
- For AI agents: terrio mcp is an MCP server, so Claude Code, Claude Desktop, Cursor or VS Code can run terrio's commands on your data.
Get it
- Command line (Linux, macOS): curl -LsSf terrio.opengeos.org/install.… | sh
- Python: pip install terrio (with rasterio- and xarray-style APIs)
- JavaScript/WebAssembly: npm install terrio-js
- Rust: cargo add terrio
Try it out
- Playground in your browser: terrio.opengeos.org/playgrou…
- Documentation: terrio.opengeos.org
- GitHub: github.com/opengeos/terrio
#GIS #Rust #OpenSource #Geospatial #Python #LiDAR #CloudNative
darshan retweeted
The video above was the Pūrvapakṣa - the questions.
Here is the Siddhānta - my answers.
Does the world change? Absolutely.
Do we adapt? 100%.
And ultimately, intelligence is not what makes us human.
Our ability to care for others and solve for others does.
Prathosh.
Dr. Pratosh at IISc Bengaluru tells his students that rapid advances in AI are commoditizing intellectual labour.
He raises an unsettling question: if companies stop recruiting on campus in the next 5–10 years—even at India’s top universities—what will the purpose of a university education be ?
A must watch video for everyone in tech
darshan retweeted
This summer, I taught an introductory class at King's College London on Generative models, and some links with mathematical transport theory.
The notes originated from my old blog posts; I decided to entirely rework them.
They now have their own website, simoncoste.gitlab.io/transpo…
🐞 smol thread below 🐞
/goal:
Achieve holistic development.
Make no mistakes
Build highly personalized assement and lessons for skill development.
Also, AI buddies for social games like Dungeons and Dragons?
Following the amazing reaction to the Marble Curriculum yesterday, we've decided to make it open source 🛰️👇
Everything a child learns in primary school. 1,590 concepts. 3,221 connections across 8 subjects, from Math and Science to Computing and Life Skills. Anchored in the US and UK curriculums, standard by standard (NGSS, Common Core, DfE).
What you will find in the repo: every concept as structured JSON with its age band and the evidence a child must show to master it. Every prerequisite link marked hard or soft, with a written rationale. It's a true DAG you can compute learning paths on. Open license, you can build whatever you want with it.
Now is a unique time in history to be building in education. Getting AI and kids education right is likely one of the hardest and most important problems to crack over the next decade and we need as many smart and creative minds behind it.
We think a common solid basis, accessible to all and that can be built upon, is critical to move fast. That's why we're making this curriculum open source.
It's not perfect but we know it's a robust basis, and we believe that sharing it openly is the fastest way to progress in this field. If you're building in education, share this around you and tell us in comments if you find this useful and if you want to contribute.
We'll keep working and investing on it @withmarbleapp. Credit goes to @guillaume_boni for building this. I just made it look pretty.
Links below 👇
53
GPT5.6 has really good taste for literature. Discovering the most relevant concepts hits the spot. 🤌🏼
I think I will be reading a lot more papers. 😁
2
114
darshan retweeted
Fable turned my remarkable into Tom Riddle's diary from Harry Potter.
My prompts fade, a LLM respond.
Magical!
Neurosymbolic RL and Agent Regret ✅ ?
Note that because of how the attention mechanism works, the tokens are really just a thin layer on top of a long series of embedding vectors composed from previous vectors, none of which are visible from the transcript.
This suggests that Fable 5's thoughts lean more on composing semantic structures with attention rather than representing it as text.
1
82
darshan retweeted
check out my /ultragoal skill
github.com/jxnl/dots/blob/ma…
darshan retweeted
I shrunk myself down to action figure size and can now interact with and explore the tiny world on my living room coffee table.
Wait until 7 seconds in 👀🛋️