Good Papers

Showing papers from Fraunhofer IOSB Show all papers

83%Must read
?Must readVote to see the score
NeurIPS 2026Karlsruhe Institute of TechnologNational University of SingaporeFraunhofer IOSBU BonnKarlsruhe Institute of TechnologTest-time compute

Rethinking Expressivity and Efficiency in Test-Time Training

E²-TTT derives a closed-form chunk-level state transition that exactly reproduces per-token update dynamics, enabling parallel training that retains temporal structure, matches chunk-wise throughput, and achieves over 90% needle-in-a-haystack accuracy at 8× training length.

Zeyun Zhong, Joya Chen, Manuel Martin, Frederik Diederichs and 2 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026 · ▲ 2 on Hugging Face · Code ★ 4

– ReadersNo votes yet
13/20 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: 13 of 20 reviewers recommend it
lenient 3/5
medium 9/10
strict 1/5
72%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Fraunhofer IOSB, FraunhoferstraßFraunhofer IOSBKarlsruhe Institute of TechnologBayesian & probabilistic methods

Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods

Pulling back the Fisher metric yields a local sensitivity tensor that bounds acquisition gradients and explains high-dimensional BO failures, leading to the FITR trust-region method that replaces lengthscale heuristics with local Fisher weights.

Saksham Kiroriwal, Julius Pfrommer, Jürgen Beyerer

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · 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 5/10
strict 1/5