Atul

[Youssef Saied @YoussefMMSaied]

1/

What happens when a denoiser trained at one noise level is reused inside an iterative sampler?

We trained SwinIR with Noise2Noise at σ=10, then dropped it unchanged into the constrained sampler of @ZKadkhodaie & @EeroSimoncelli (NeurIPS ’21) for 10% random inpainting.

Baseline SwinIR: 6.08 dB on Set12.

SwinIR-WNE: 23.87 dB.

Same backbone. Same N2N pairs. Same sampler.

With François Fleuret @francoisfleuret. ICML 2026. 🧵

[Atul @atulku]

Our paper "SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics" with @francoisfleuret, @DanielePaliotta, @balintmate_, @TGolling and others is accepted at #NeurIPS2023 Datasets and Benchmarks track.

https://t.co/1WwEl0neer

@unige_en

[Daniele Paliotta @DanielePaliotta]

Can you train GNNs without backprop? We extend the forward-forward algorithm to graph property prediction tasks, and the results are promising.

Joint work with @miniapeur @balintmate_ @francoisfleuret.

https://t.co/K6ee56TlNH

1/N

[François Fleuret @francoisfleuret]

There are densities for which a simple analytically defined interpolation from a normal results in mods "growing out of nowhere" instead of "sliding" there.

This makes the transport field super hard to learn since it cannot just follow them.

[Bálint Máté @balintmt]

Preprint on interpolating between unnormalized densities: https://t.co/ig8iKMs0wp
We introduce an objective for training continuous NFs without samples but with a given, non-normalized target energy that we can evaluate pointwise. Joint work with @francoisfleuret. (1/9)

[9GAG ❤️ Memeland @9GAG]

Napping is the best part of every day

[Atul @atulku]

@ankan_bansal first and second-last, hilarious! :P :D

[Atul @atulku]

@ankan_bansal I don't think it was, was it ?

[Atul @atulku]

@arunkants @ankan_bansal wohoo..hilarious!

[Atul @atulku]

@ShivaAsapu @arunkants then let me take a guess, its sunset..right? :P

[Atul @atulku]

@ShivaAsapu :D

[Atul @atulku]

Asking the right questions takes as much skill as giving the right answers.

#copied

[Atul @atulku]

22 Unbelievable Places that are Hard to Believe Really Exist :D

http://t.co/JgZ6V6pWcW