Good Papers

Showing papers from AXXX Show all papers

72%Highly rated
?Highly ratedVote to see the score

Unlocking the Duality between Flow and Field Matching

CFM and forward-only IFM are equivalent via a bijection, but general IFM is strictly more expressive, yielding cross-framework techniques.

Daniil Shlenskii, Alexander Varlamov, Nazar Buzun, Aleksandr Korotin

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
8/20 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: 8 of 20 reviewers recommend it
lenient 2/5
medium 4/10
strict 2/5
70%Highly rated
?Highly ratedVote to see the score

Midpoint Generative Models

Midpoint Generative Models define a midpoint divergence from flow matching symmetry to train one-step generators with competitive results.

Daniil Shlenskii, Nikita Gushchin, Lev Novitskiy, Dmitry V. Dylov and 1 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
5/20 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: 5 of 20 reviewers recommend it
lenient 2/5
medium 3/10
strict 0/5
80%Must read
?Must readVote to see the score

TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models

TUBE introduces a variational upper bound with unbiased Monte Carlo estimation to evaluate discrete diffusion model log-likelihoods, revealing that block diffusion and any-order autoregressive models remain below exact autoregressive baselines.

Arseny Ivanov, Sergei Kholkin, Vladislav Gromadskii, Grigoriy Ksenofontov and 2 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

– 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 4/5
medium 6/10
strict 2/5