Valentin Wagner
LightNews LightNews
banner
valentinwagner.bsky.social
Valentin Wagner
@valentinwagner.bsky.social
670 followers 690 following 5 posts
3D Reconstruction / Earth Observation / Researcher @ Fraunhofer IOSB (Germany) / PHD Student @ KIT
Posts Replies Media Videos
Reposted by Valentin Wagner
weinzaepfelp.bsky.social
When were #ICCV2025 papers available on arXiv? 👇
October 27, 2025 at 6:21 AM
Reposted by Valentin Wagner
wimmerthomas.bsky.social
Super excited to introduce

✨ AnyUp: Universal Feature Upsampling 🔎

Upsample any feature - really any feature - with the same upsampler, no need for cumbersome retraining.
SOTA feature upsampling results while being feature-agnostic at inference time.

🌐 wimmerth.github.io/anyup/
October 16, 2025 at 9:07 AM
Reposted by Valentin Wagner
wjscheirer.bsky.social
The #ICCV2025 main conference open access proceedings is up:

openaccess.thecvf.com/ICCV2025

Workshop papers will be posted shortly. Aloha!
October 14, 2025 at 7:42 PM
Reposted by Valentin Wagner
timkellogg.me
Karpathy: nanochat

A small training+inference pipeline for creating your own LLM from scratch

$100 will get you a somewhat functional model

$1000 is more coherent & solves math

detailed walkthrough: github.com/karpathy/nan...

repo: github.com/karpathy/nan...
Andrej Karpathy & @karpathy X.com Excited to release new repo: nanochat! (it's among the most unhinged I've written). Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single, dependency-minimal codebase. You boot up a cloud GPU box, run a single script and in as little as 4 hours later you can talk to your own LLM in a ChatGPT-like web Ul. It weighs ~8,000 lines of imo quite clean code to: - Train the tokenizer using a new Rust implementation - Pretrain a Transformer LLM on FineWeb, evaluate CORE score across a number of metrics - Midtrain on user-assistant conversations from SmolTalk, multiple choice questions, tool use. - SFT, evaluate the chat model on world knowledge multiple choice (ARC-E/C, MMLU), math (GSM8K), code (HumanEval) - RL the model optionally on GSM8K with IPDDOI - RL the model optionally on GSM8K with "GRPO" - Efficient inference the model in an Engine with KV cache, simple prefill/ decode, tool use (Python interpreter in a lightweight sandbox), talk to it over CLI or ChatGPT-like WebUl. - Write a single markdown report card, summarizing and gamifying the whole thing. Even for as low as ~$100 in cost (~4 hours on an 8XH100 node), you can train a little ChatGPT clone that you can kind of talk to, and which can write stories/poems, answer simple questions. About ~12 hours surpasses GPT-2 CORE metric. As you further scale up towards ~$1000 (~41.6 hours of training), it quickly becomes a lot more coherent and can solve simple math/code problems and take multiple choice tests. E.g. a depth 30 model trained for 24 hours (this is about equal to FLOPs of GPT-3 Small 125M and 1/1000th of GPT-3) gets into 40s on MMLU and 70s on ARC-Easy, 20s on GSM8K, etc. My goal is to get the full "strong baseline" stack into one cohesive, minimal, readable, hackable, maximally forkable repo. nanochat will be the capstone project of LLM101n (which is still being developed). I think it also has potential to grow developed). I think it also has potential to grow into a research harness, or a benchmark, similar to nanoGPT before it. It is by no means finished, tuned or optimized (actually I think there's likely quite a bit of low-hanging fruit), but I think it's at a place where the overall skeleton is ok enough that it can go up on GitHub where all the parts of it can be improved. Link to repo and a detailed walkthrough of the nanochat speedrun is in the reply. nanochat
October 13, 2025 at 6:06 PM
Reposted by Valentin Wagner
nicolang.bsky.social
Working on representation learning for Earth Observation?
Come join the discussion at the EurIPS workshop "REO: Advances in Representation Learning for Earth Observation"

Call for papers deadline: October 15, AoE
Workshop site: sites.google.com/view/reoeurips

@euripsconf.bsky.social @esa.int
October 9, 2025 at 12:32 PM
Reposted by Valentin Wagner
3dvconf.bsky.social
🐝 The #3DV2026 Nectar Track is open for submissions!
1️⃣ Spotlight Track: Showcase your strong paper from recent venues with an oral presentation + poster.
2️⃣ Exploration Edge Track: Present preliminary ideas, research hurdles, or demos in a poster session.
More details: ⬇️
September 30, 2025 at 1:37 AM
Reposted by Valentin Wagner
cvprconference.bsky.social
This marks the kick-off of our #CVPR2026 coverage! I’m @csprofkgd.bsky.social, and more publicity chairs will be joining in soon.

The key #CVPR2026 dates are now posted. One highlight: the supplementary materials deadline comes a full week AFTER the main paper deadline.
September 28, 2025 at 10:54 PM
Reposted by Valentin Wagner
ericzzj.bsky.social
MapAnything: Universal Feed-Forward Metric 3D Reconstruction

@nikv9.bsky.social et al.

tl;dr: flexible input & metric output version of VGGT

arxiv.org/abs/2509.13414
September 18, 2025 at 10:57 AM
valentinwagner.bsky.social
Great to see more initiatives to bring conferences/events to Europe 🇪🇺. Reducing unnecessary co2 emissions caused by long-distance flights and simultaneously strengthening europe as research location.
euripsconf.bsky.social EurIPS Conference @euripsconf.bsky.social · Jul 16
EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅

EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu

eurips.cc
July 17, 2025 at 7:34 AM
Reposted by Valentin Wagner
csprofkgd.bsky.social
#ICML2025 test of time award
July 15, 2025 at 2:06 AM
Reposted by Valentin Wagner
simonwillison.net
The is diabolical... a Python object that hallucinates method implementations on demand any time you call them, using my LLM Python library github.com/awwaiid/grem...
from gremllm import Gremllm # Be sure to tell your gremllm what sort of thing it is counter = Gremllm('counter') counter.value = 5 counter.increment() print(counter.value) # 6? print(counter.to_roman_numerals()) # VI?
July 4, 2025 at 5:39 PM
Reposted by Valentin Wagner
pesarlin.bsky.social
We just released COLMAP v3.12, which adds long-awaited, end-to-end support for multi-camera rigs and 360° panoramas 👀 COLMAP just got better at handling your robotics, AR/VR, or 360 data - try it yourself and let us know! github.com/colmap/colma... Kudos to Johannes & team for this great work 🚀
July 1, 2025 at 4:33 PM
Reposted by Valentin Wagner
cvprconference.bsky.social
#CVPR2025 paper statistics
June 13, 2025 at 2:16 PM
Reposted by Valentin Wagner
wjscheirer.bsky.social
The #CVPR2025 main conference open access proceedings is up:

openaccess.thecvf.com/CVPR2025

Workshop papers will be posted shortly. Stay tuned...
June 3, 2025 at 2:46 PM
Reposted by Valentin Wagner
wacvconference.bsky.social
The #WACV2026 Call for Papers is live at wacv.thecvf.com/Conferences/...! First round paper registration is coming up on July 11th, with the submission deadline on July 18th (all deadlines are 23:59 AoE).
A screenshot of the important dates for the WACV2026 submission process.
May 27, 2025 at 5:40 PM
Reposted by Valentin Wagner
sattlertorsten.bsky.social
Working on camera calibration or camera pose estimation? Want to finally know how calibrations and poses are obtained for the data you ae using?
Come join us at the CALIPOSE workshop at @iccv.bsky.social

Details are on the workshop website: sites.google.com/view/calipos...
Camera Calibration and Pose Estimation (CALIPOSE)
Workshop Information When: October 19th or 20th, 2025 Where: Honolulu, Hawai'i, ICCV 2025 Time: TBD Preliminary Schedule Opening [all organizers, 5 mins] Invited Talk I: Richard Hartley [30 mins] Inv...
sites.google.com
May 27, 2025 at 11:43 AM
Reposted by Valentin Wagner
zacklabe.com
Mosaic of daily #Arctic sea-ice extent anomalies over the last four decades or so. Another way of visualizing the long-term trend.

Graphic from zacklabe.com/arctic-sea-i...
Heat-map style graphic of Arctic sea ice extent anomalies for every day from 1 January 1979 through 31 December 2024. Blue shading is shown for greater sea ice, and red shading is shown for less sea ice. The baseline is 1981 to 2010. The graphic is in units of million square kilometers from -3 to +3. Data from NSIDC.
May 18, 2025 at 11:14 PM
Reposted by Valentin Wagner
adai.bsky.social
🚀Join the 𝐒𝐜𝐚𝐧𝐍𝐞𝐭++ 𝐂𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐞 @ CVPR 2025!
Think your method can handle large-scale 3D scenes?
Put it to the test:
kaldir.vc.in.tum.de/scannetpp/cv...

Updates:
✅ Preprocessed, undistorted DSLR images
✅ 3DGS demo: github.com/scannetpp/3D...

by Yueh-Cheng Liu, @cyeshwanth.bsky.social
May 1, 2025 at 12:16 PM
valentinwagner.bsky.social
Great thread about the evolution of radiance fields!
jonbarron.bsky.social Jon Barron @jonbarron.bsky.social · Apr 8
A thread of thoughts on radiance fields, from my keynote at 3DV:

Radiance fields have had 3 distinct generations. First was NeRF: just posenc and a tiny MLP. This was slow to train but worked really well, and it was unusually compressed --- The NeRF was smaller than the images.
April 26, 2025 at 5:04 PM
Reposted by Valentin Wagner
nicolasdufour.bsky.social
🌍 Guessing where an image was taken is a hard, and often ambiguous problem. Introducing diffusion-based geolocation—we predict global locations by refining random guesses into trajectories across the Earth's surface!

🗺️ Paper, code, and demo: nicolas-dufour.github.io/plonk
December 10, 2024 at 3:56 PM
Reposted by Valentin Wagner
iclr-conf.bsky.social
Announcing the Test of Time awards for ICLR 2025! This award recognizes papers published ten years ago at ICLR 2015 that have had a lasting impact on the field. Congratulations to the authors!

blog.iclr.cc/2025/04/14/a...
Announcing the Test of Time Award Winners from ICLR 2015 – ICLR Blog
blog.iclr.cc
April 15, 2025 at 3:39 AM
valentinwagner.bsky.social
Great tool to keep up to date with papers and for finding related works 📚
andreasgeiger.bsky.social Andreas Geiger @andreasgeiger.bsky.social · Apr 14
🚀 Never miss a beat in science again!

📬 Scholar Inbox is your personal assistant for staying up to date with your literature. It includes: visual summaries, collections, search and a conference planner.

Check out our white paper: arxiv.org/abs/2504.08385
#OpenScience #AI #RecommenderSystems
April 14, 2025 at 12:05 PM
Reposted by Valentin Wagner
antoine-guedon.bsky.social
💻We've released the code for our #CVPR2025 paper MAtCha!

🍵MAtCha reconstructs sharp, accurate and scalable meshes of both foreground AND background from just a few unposed images (eg 3 to 10 images)...

...While also working with dense-view datasets (hundreds of images)!
April 3, 2025 at 10:33 AM
Reposted by Valentin Wagner
ducha-aiki.bsky.social
#IMC2025 @cvprconference.bsky.social challenge is online!
This year:
- back to collection_mapping: directory with many (similar) scenes->your job to SfM & cluster them
- a bit more of training set
- no transparent objects

$50000 prize fund
Deadline: June 2
www.kaggle.com/competitions...
#IMW2025
Image Matching Challenge 2025
Reconstruct 3D scenes from messy image collections.
www.kaggle.com
April 1, 2025 at 9:02 PM