Christian Wolf

Memory Caching: RNNs with growing memory Behrouz et al. arxiv.org/abs/2602.24281 Take different RNNs and, and at time t don't read out only M_t, but cached previous hidden memories. Neat and effective. Tested on different modern RNN variants.

Memory Caching: RNNs with Growing Memory arxiv.org

When projected onto a map, the attention maps correlate with scene structure and with affordances related to the scene structure. These maps have been computed on real nav data in a real environment (like ALL results in this paper). More results in the paper: arxiv.org/abs/260…

A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world arxiv.org

This is work at Naver Labs Europe by - Philippe Weinzaepfel (@weinzaepfelp.bsky.social) - Yours truly, - Mert Bulent Sariyildiz (@mbsariyildiz.bsky.social) - Guillaume Bono, - Gianluca Monaci arxiv.org/abs/2606.21562 7/8

Compressing Observation History into Agent Memory: Distilling Transformers into Recurrent Transformers arxiv.org

Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models Yang,Lin,Martin-Martin,Labrie,Gayaka,Kuo,Carlone Put VGGT into VLA. Early fusion (before VLM) > late fusion (after VLM) Impact of 3D (VGGT) highest in single camera setup (!?!) arxiv.org/a…

Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models arxiv.org

For your Embodied AI task you want a recurrent model with constant complexity per step, but you don't want to lose the power of transformers (which store the full obs history and attend to it)? Do not despair, we have your back. We distill transformers into recurrent transformers 1/8

My Dad made fun of me for my use of "please" when talking to Claude. His point: the AI does not care. My point: this is not about the AI but about me.

Excellent Keynote by @akorba.bsky.social at Cap-Rfiap in Montpellier, France, on machine learning and distances between distributions.

ICRA panel on the impact of AI and the paper avalanche on robotics conferences and journals. The same problems arrise in ML and in CV of course.

Grading students' exam copies the first time since 2021. I forgot about that "enjoyable" part of a prof's job (left to industry but I am doing 1 small course on deep learning for control this year).

Don't use LLMs in your conversations with me please. It might have an emotional effect on the conversation which I cannot easily control.

LLMs passed the ultimate usefulness test: my Dad sent a WhatsApp message asking for help on a computer problem. Then came a follow-up message, AI solved it.

La seule chose que j'ai envie de dire de cette thèse Grenobloise tristement célèbre, c'est que le doctorant en question semble avoir eu des collègues de laboratoire fortement sympathiques! Il est très dommage qu'il n'a pas trouvé plus d'inspiration.