Nikita Araslanov

@neekans

Researcher at University of Oxford / TU Munich

Munich

arnike.github.io

Joined February 2009

Pinned
Nikita Araslanov
@neekans
May 28
In-context learning suggests that a model has learned versatile representations. What if we use in-context learning itself as a training task for visual representations? 📣 Introducing 𝗟𝗜𝗟𝗔: 𝗟𝗶𝗻𝗲𝗮𝗿 𝗜𝗻-𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 ✨ @CVPR 2026 Oral ✨ 𝗟𝗜𝗟𝗔
00:00
Nikita Araslanov
@neekans
Dec 2, 2025
📢 NeurIPS 2025 Spotlight 📢 Can we embed motion into image representations? Trained on videos, FlowFeat embeds optical flow into pixel-level representations (up to a linear transform), which results in sharp feature grids, especially for dynamic objects. We demonstrate
00:00
Nikita Araslanov
@neekans
Oct 19, 2025
#ICCV2025 Spotlight talk (SP4V Workshop) Training on videos should yield more 3D-aware models than images — but it doesn’t! Presenting The Diashow Paradox in our talk, 16:15 @ 323A. With Tien Duc Nguyen (@hoaquin10), Anna Sonnweber, Mark Weber, Daniel Cremers (@tumcvg)
Nikita Araslanov
@neekans
Jun 4, 2025
The implication is quite exciting: unsupervised classifiers. We can assign semantic labels to visual data without any paired data, at least for some semantic concepts. #CVPR2025
Dominik Schnaus
@dominik_schnaus
Jun 3, 2025
Can we match vision and language representations without any supervision or paired data? Surprisingly, yes! Our #CVPR2025 paper with @neekans and Daniel Cremers shows that the pairwise distances in both modalities are often enough to find correspondences. ⬇️1/4
00:00
Nikita Araslanov
@neekans
Oct 3, 2024
How to recover accurate shapes from noisy point clouds? Find out at poster *214* in the last session of #ECCV2024!
Linus Härenstam-Nielsen
@LinusHNielsen
Jul 29, 2024
Very excited to announce our paper: "DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting" at #ECCV2024! Paper: arxiv.org/abs/2407.17058 Code/project: github.com/linusnie/diffcd