no

[Jonathan @ICML @lightetal]

Incredibly honored to receive the Outstanding Paper Award at the Logical Reasoning Workshop at #ICLR2026, on behalf of my coauthors and myself.

Huge thanks to the workshop organizers, including @witbrock and @armancohan, and @iclr_conf!

[Kacper Wyrwal @WyrwalKacper]

Super excited to be at @iclr_conf in Rio! I'll be presenting "Topological Flow Matching" in collaboration with the amazing @ismaililkanc and @AlexanderTong7.

We improve flow matching performance for modelling signals on graphs and simplicial complexes by aligning sample paths with heat diffusion.

Find out more at the poster!

🗓️ Friday, April 24, 2026
​🕒 3:15 PM - 5:45 PM BRT
​📍 Pavilion 3 · Poster P3-#820

[Ravid Shwartz Ziv @ziv_ravid]

New episode of The Information Bottleneck is out, this time with @liuzhuang1234 (Princeton).

We talked about ConvNeXt and whether architecture still matters; dataset bias and what "good data" actually looks like; ImageBind and why vision is the natural bridge across modalities; CLIP's blind spots; memory as the real bottleneck behind the agent hype; whether LLMs have world models; and Transformers Without Normalization.

For years, the vision community debated what actually matters: architecture, inductive bias, self-attention vs convolution. After a lot of back-and-forth, we ended up in a funny place: ViT and ConvNet give roughly the same performance once you tune the details.

What I find interesting is that once you reach a certain performance level, it becomes much easier to swap and tweak components without really changing the outcome.

Talking to Zhuang on this episode, I kept wondering whether the same is now true for LLMs. If we wil spent serious time on an alternative architecture today, would you actually get a meaningfully different model, or just land on the same Pareto curve with extra steps?

I'm starting to suspect it's the latter. Architecture matters less than we think. Data, compute, and a handful of pillars do most of the work.