Principal Scientist, @NaverLabsEurope, Lead of Spatial AI team. AI for Robotics. Feedback: https://xitter.cf/t.co/uD0Z0OSHEX
Lyon, France
Joined November 2015
- Tweets5.9K
- Following747
- Followers8.6K
- Likes10.1K
Having fun with Blender ...
Distilling context transformers into recurrent transformers:
arxiv.org/abs/2606.21562
@WeinzaepfelP @mbsariyildiz @_WGW101
Christian Wolf (🦋🦋🦋) retweeted
Our second call for NeurIPS Paris 2026 volunteers will open tomorrow TUE Oct 6th, 2pm CET.
We are still seeking for PhD students and postdocs to assist during the conference in exchange for complimentary registration.
Application form:
forms.gle/bBFUyUNngtCcEN3z8
ECCV Poster #305 3pm now: A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world
@JannySteeven, L. Antsfeld, myself (I will present)
Visual enc distilled from heterog. teachers
Attention proj
Pretrain Policy w Lidar input => remove Lidar
Evaluated on 966 real navigation episodes:
real robot, real building
arxiv.org/abs/2606.21216
Christian Wolf (🦋🦋🦋) retweeted
NeurIPS is approaching and registration for the Paris site will be opened on Monday Sept 14th, Anywhere on Earth.
Registration happens at neurips.cc, each of the 3 sites has its own registration process.
We'll be happy to see you in Paris!
Christian Wolf (🦋🦋🦋) retweeted
🧐 Can you distill knowledge from 4 vision teachers into one student using ZERO real images?
🥳 Turns out: YES, and surprisingly well.
📢 Our ECCV 2026 paper "IDeaL" closes most of the gap with real-image distillation, using optimized structured noise.
Papers on recurrent transformers: arxiv.org/pdf/2606.21562 (ours): train full Tr, distill -> rec Tr
arxiv.org/pdf/2608.02870 train full and rec jointly, max. coherence
arxiv.org/pdf/2606.06479 train rec Tr w predict. obj.
arxiv.org/pdf/2608.08888 train full Tr, add rec latents
Christian Wolf (🦋🦋🦋) retweeted
Evening walk and read. I’ve been looking forward to reading this paper. – at Zurich, Switzerland
Christian Wolf (🦋🦋🦋) retweeted
*NEW* Our #ECCV2026 @eccvconf paper
Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation
Now on ArXiv w Dataset, Code&model
sid2697.github.io/epic-conta…
arxiv.org/abs/2606.30598
Two contributions:
1. EPIC-Contact Dataset
2. HOPformer Method &Checkpoint
🧵 1/6
#ECCV2026 paper: A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world
966 *REAL* nav episodes by S. Janny with Dino-v3, Dino-v2, DUNE, VC1, AM-RADIO encoders show that patch features can be bottlenecked to 1 value ➡️ affordances.
1/8
Projected onto a map, the attention maps correlate with scene structure and with affordances related to it. These maps have been computed on real nav data in a real environment (like ALL results in this paper).
More results:
arxiv.org/abs/2606.21216
ECCV 2026
8/8
Christian Wolf (🦋🦋🦋) retweeted
Our #ECCV2026 @eccvconf paper
Gen2Balance: Generative Balancing for Long-Tailed Video Action Recognition
now on ArXiv w/ code&data&models
prajwalgatti.github.io/gen2b…
Can we fill imbalanced action recognition datasets with generative images to outperform long-tail SOTA?
Yes we can
🧵