Good Papers

Showing papers from Inria Paris / ENS Show all papers

80%Must read
?Must readVote to see the score
NeurIPS 2026École PolytechniqueINRIAInria Paris / ENSMohamed bin Zayed University of CMU/MBZUAI/GenBioDiffusion models

Uniform Diffusion Models revisited: Leave-One-Out Denoiser and Absorbing State Reformulation

Standard uniform diffusion training uses a leave-one-out posterior rather than the true denoising posterior, causing a parameterization-objective mismatch that new conversions, samplers, and an absorbing-state reformulation fix to match masked diffusion.

Samson Gourevitch, Yazid Janati, Dario Shariatian, Umut Simsekli and 3 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026 · ▲ 4 on Hugging Face · Code ★ 11

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 3/5
medium 7/10
strict 2/5
71%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U OxfordInria Paris / ENSU CopenhagenDiffusion models

Metropolis-Adjusted Diffusion Models

Metropolis-adjusted Langevin correctors using score-based acceptance probabilities and a two-coin Bernoulli factory reduce diffusion model sampling bias and improve FID.

Kevin H. Lam, Tyler Farghly, Christopher Williams, Jun Yang and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
6/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 6 of 20 reviewers recommend it
lenient 2/5
medium 4/10
strict 0/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026INRIAImperial College LondonInria Paris / ENSDeep learning theory

Generalization at the Edge of Stability

Stochastic optimizers at the edge of stability converge to low-dimensional fractal attractors, and a sharpness-dimension generalization bound reveals that chaotic training depends on the full Hessian spectrum.

Mario Tuci, Caner Korkmaz, Umut Simsekli, Tolga Birdal

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · Code ★ 10

– ReadersNo votes yet
11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 11 of 20 reviewers recommend it
lenient 2/5
medium 6/10
strict 3/5