Good Papers

Showing papers from Zuse Institute Berlin Show all papers

57%Worth a look
?Worth a lookVote to see the score

A Free Lunch in LLM Compression: Revisiting Retraining after Pruning

Moritz Wagner, Christophe Roux, Max Zimmer, Sebastian Pokutta

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
1/20 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: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score

A Trust Region Approach for Learning Schrödinger Bridges

Takeshi Koshizuka, Denis Blessing, Max Zimmer, Sebastian Pokutta and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 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: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
71%Highly rated
?Highly ratedVote to see the score

Curvature-Dependent Lower Bounds for Frank-Wolfe

Frank-Wolfe achieves Ω(T^{-p/(p-1)}) lower bounds on p-uniformly convex sets for p ≥ 3 under exact line search or short steps, matching upper bounds via low-dimensional dynamics.

Jannis Halbey, Christophe Roux, Sebastian Pokutta

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

– ReadersNo votes yet
7/20 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: 7 of 20 reviewers recommend it
lenient 1/5
medium 4/10
strict 2/5
74%Highly rated
?Highly ratedVote to see the score

Frank-Wolfe Beyond 1/t Convergence

A local dual sharpness condition enables Frank-Wolfe to converge faster than 1/t on uniformly convex sets, bypassing standard lower bounds.

Sebastian Pokutta

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
9/20 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: 9 of 20 reviewers recommend it
lenient 1/5
medium 6/10
strict 2/5