Claims Browser

The orthogonality among principal subspaces of the Fisher information matrix's K-FAC approximation, estimated from a small number of downstream task samples, can reflect the similarity between different tasks in pre-trained models

"a key observation about the Fisher information matrix (FIM) of pre-trained models: the orthogonality among the principal subspaces of its Kronecker-Factored Approximate Curvature (K-FAC) approximation, estimated from a small number of downstream task samples, can reflect the similarity between different tasks."

Little is known about how representation learning methods deal with out-of-domain speech and how they could be adapted in a few shot to new domains

"little is known about how such methods deal with out-of-domain speech and how could they be adapted in a few shot to new domains"

Permutation-equivariant architectures are motivated by the fact that graphs are invariant under node permutations

"Graphs are invariant under node permutations, motivating the use of permutation-equivariant architectures in generative models."

The natural Wasserstein geometry for graph pairs compared up to node relabeling is that of the graph quotient space

"once graph pairs are compared up to node relabeling, the natural Wasserstein geometry is that of the graph quotient space"

The Euclidean quotient metric coincides with the Gromov-Monge distance obtained by optimally relabeling nodes

"The Euclidean quotient metric of this space coincides with the Gromov--Monge distance, obtained by optimally relabeling the nodes."

Quotient couplings can be lifted to aligned representatives without additional cost

"quotient couplings can be lifted to aligned representatives without additional cost"

Structure-aware couplings substantially improve sample quality at small integration budgets in graph and molecular generation

"these structure-aware couplings substantially improve sample quality at small integration budgets"

The proposed molecular models remain competitive under conventional many-step sampling when scaled up

"our scaled-up molecular models remain competitive under conventional many-step sampling"

Representation learning has reached good performances as a pretraining method for downstream tasks and as a first step towards unsupervised speech modeling

"Representation learning has attracted great atten- tion and managed to reach good performances as a pretraining method for downstream tasks or as a first step towards unsu- pervised speech modeling"

Foundation models for chemistry, agentic workflows, simulation, and automated experimentation are dramatically accelerating the search for new materials

"foundation models for chemistry, agentic workflows, simulation, and automated experimentation are dramatically accelerating the search for new materials and reshaping scientific discovery."

Symmetrization yields equivariant flow-matching minimizers, including for categorical endpoint prediction

"symmetrization yields equivariant flow-matching minimizers, including for categorical endpoint prediction"

A randomized study involving over 1,000 students has been conducted examining the relationship between ChatGPT usage and critical thinking, originality, and student performance on university assignments

"A randomized study of more than 1,000 students examines ChatGPT, critical thinking, originality, and student performance on a real-world university assignment."

For the d-expert problem, the minimax alternating regret is Θ(log d), independent of the horizon T

"for the $d$-expert problem, we show that the minimax alternating regret is $Θ(\log d)$, independent of the horizon $T$"

The new result significantly improves upon the best-known O(T^(1/3) log^(2/3) d) bound established by Hait et al. (2025)

"This significantly improves upon the best-known $\mathcal{O}(T^{1/3}\log^{2/3} d)$ established by Hait et al. [2025]"

For general OCO over a d-dimensional compact convex set, the worst-case minimax alternating regret is Θ(d log(1 + T/d))

"We further extend our results to general OCO over a $d$-dimensional compact convex set and prove that the worst-case minimax alternating regret is $Θ\left(d\log \left(1+\frac{T}{d}\right)\right)$"

The new OCO bound resolves the open problem posed by Cevher et al. (2023) and Hait et al. (2025) and improves upon the best-known O((d log T)^(2/3) T^(1/3)) upper bound

"also significantly improving upon the best-known $\mathcal{O}((d\log T)^{2/3}T^{1/3})$ upper bound and resolving the open problem posed by Cevher et al. [2023], Hait et al. [2025]"

The upper bound for the expert problem is achieved by a corrected variant of Hedge with carefully designed correction terms that cancel the unfavorable curvature in alternating-regret analysis

"our upper bound for the expert problem is achieved by a corrected variant of Hedge, in which carefully designed correction terms cancel the unfavorable curvature arising in the alternating-regret analysis"

ChatGPT is being used by students and educators to make learning more continuous with support extending beyond the classroom

"students and educators use ChatGPT to make learning more continuous, with support that extends beyond the classroom"