Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2410.01104
Cited By
softmax is not enough (for sharp out-of-distribution)
1 October 2024
Petar Veličković
Christos Perivolaropoulos
Federico Barbero
Razvan Pascanu
Re-assign community
ArXiv
PDF
HTML
Papers citing
"softmax is not enough (for sharp out-of-distribution)"
12 / 12 papers shown
Title
Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models
Hector Pasten
Felipe Urrutia
Hector Jimenez
Cristian B. Calderon
Cristóbal Rojas
Alexander Kozachinskiy
12
0
0
15 May 2025
Knowledge Distillation for Speech Denoising by Latent Representation Alignment with Cosine Distance
Diep Luong
Mikko Heikkinen
K. Drossos
Tuomas Virtanen
47
0
0
06 May 2025
Bayesian Principles Improve Prompt Learning In Vision-Language Models
Mingyu Kim
Jongwoo Ko
Mijung Park
VLM
43
0
0
19 Apr 2025
Long Context In-Context Compression by Getting to the Gist of Gisting
Aleksandar Petrov
Mark Sandler
A. Zhmoginov
Nolan Miller
Max Vladymyrov
27
0
0
11 Apr 2025
On Vanishing Variance in Transformer Length Generalization
Ruining Li
Gabrijel Boduljak
Jensen
Zhou
38
0
0
03 Apr 2025
Multi-Token Attention
O. Yu. Golovneva
Tianlu Wang
Jason Weston
Sainbayar Sukhbaatar
48
1
0
01 Apr 2025
TRA: Better Length Generalisation with Threshold Relative Attention
Mattia Opper
Roland Fernandez
P. Smolensky
Jianfeng Gao
46
0
0
29 Mar 2025
Attend or Perish: Benchmarking Attention in Algorithmic Reasoning
Michal Spiegel
Michal Štefánik
Marek Kadlcík
Josef Kuchař
37
0
0
28 Feb 2025
Hallucination Detection in LLMs Using Spectral Features of Attention Maps
Jakub Binkowski
Denis Janiak
Albert Sawczyn
Bogdan Gabrys
Tomasz Kajdanowicz
65
0
0
24 Feb 2025
What makes a good feedforward computational graph?
Alex Vitvitskyi
J. G. Araújo
Marc Lackenby
Petar Velickovic
85
1
0
10 Feb 2025
Round and Round We Go! What makes Rotary Positional Encodings useful?
Federico Barbero
Alex Vitvitskyi
Christos Perivolaropoulos
Razvan Pascanu
Petar Velickovic
75
16
0
08 Oct 2024
MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
Renchunzi Xie
Ambroise Odonnat
Vasilii Feofanov
Weijian Deng
Jianfeng Zhang
Bo An
46
2
0
29 May 2024
1