Atul retweeted
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. 🧵
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.
arxiv.org/abs/2202.05012
@unige_en
Atul retweeted
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.
arxiv.org/abs/2302.05282
1/N
Atul retweeted
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.
Atul retweeted
Preprint on interpolating between unnormalized densities: arxiv.org/abs/2301.07388
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)
Asking the right questions takes as much skill as giving the right answers.
#copied
1
1
22 Unbelievable Places that are Hard to Believe Really Exist :D
boredpanda.com/amazing-place…








