Tootfinder

World's
Tiniest
Violin
OpenAI accuses New York Times of hacking AI models in copyright lawsuit
https://cointelegraph.com/news/openai-new-york-times-hacking-ai-models

Neural Architecture Search for Sentence Classification with BERT
Philip Kenneweg, Sarah Schr\"oder, Barbara Hammer
https://arxiv.org/abs/2403.18547 ht…

Neural Architecture Search for Sentence Classification with BERT
Pre training of language models on large text corpora is common practice in Natural Language Processing. Following, fine tuning of these models is performed to achieve the best results on a variety of tasks. In this paper we question the common practice of only adding a single output layer as a classification head on top of the network. We perform an AutoML search to find architectures that outperform the current single layer at only a small compute cost. We validate our classification architec…

This https://arxiv.org/abs/2310.10500 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qfi…

Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies
Forecasting models for systematic trading strategies do not adapt quickly when financial market conditions rapidly change, as was seen in the advent of the COVID-19 pandemic in 2020, causing many forecasting models to take loss-making positions. To deal with such situations, we propose a novel time-series trend-following forecaster that can quickly adapt to new market conditions, referred to as regimes. We leverage recent developments from the deep learning community and use few-shot learning. …

This https://arxiv.org/abs/2008.01887 has been replaced.
link: https://scholar.google.com/scholar?q=a

Finite-time blow-up prevention by logistic source in parabolic-elliptic chemotaxis models with singular sensitivity in any dimensional setting
In recent years, a lot of attention has been drawn to the question of whether logistic kinetics is sufficient to enforce the global existence of classical solutions or to prevent finite-time blow-up in various chemotaxis models. The current paper is to study the above question for the following parabolic-elliptic chemotaxis system with singular sensitivity and logistic source in any space dimensional setting, \begin{equation} \begin{cases} u_t=Δu-χ\nabla\cdot (\frac{u}{v} \nabla v)+u(a(x,t)-b…

This https://arxiv.org/abs/2305.18983 has been replaced.
link: https://scholar.google.com/scholar?q=a

SO(2)-Equivariant Downwash Models for Close Proximity Flight
Multirotors flying in close proximity induce aerodynamic wake effects on each other through propeller downwash. Conventional methods have fallen short of providing adequate 3D force-based models that can be incorporated into robust control paradigms for deploying dense formations. Thus, learning a model for these downwash patterns presents an attractive solution. In this paper, we present a novel learning-based approach for modelling the downwash forces that exploits the latent geometries (i.e.…

Today I am very confused about how the bird detector is failing to spot birds on the video stream but if I run it against the analysed frames (which are saved out in debug mode) using the same model, code, etc., it finds them.

"AI" isn't going to take over the world until it's reliable and going off my experiences with that, it's a long way off.

(and that's not even getting into the inability to use different models because REASONS)

The Logic of Correct Models
Juan Pablo Aguilera, Fedor Pakhomov
https://arxiv.org/abs/2402.15382 https://arxiv.org/pdf/2402.15382

The Logic of Correct Models
For each $n\in\mathbb{N}$, let $[n]ϕ$ mean "the sentence $ϕ$ is true in all $Σ_{n+1}$-correct transitive sets." Assuming Gödel's axiom $V = L$, we prove the following graded variant of Solovay's completeness theorem: the set of formulas valid under this interpretation is precisely the set of theorems of the linear provability logic GLP.3. We also show that this result is not provable in ZFC, so the hypothesis V = L cannot be removed. As part of the proof, we derive (in ZFC) the following pu…

This https://arxiv.org/abs/2008.01887 has been replaced.
link: https://scholar.google.com/scholar?q=a

Finite-time blow-up prevention by logistic source in parabolic-elliptic chemotaxis models with singular sensitivity in any dimensional setting
In recent years, a lot of attention has been drawn to the question of whether logistic kinetics is sufficient to enforce the global existence of classical solutions or to prevent finite-time blow-up in various chemotaxis models. The current paper is to study the above question for the following parabolic-elliptic chemotaxis system with singular sensitivity and logistic source in any space dimensional setting, \begin{equation} \begin{cases} u_t=Δu-χ\nabla\cdot (\frac{u}{v} \nabla v)+u(a(x,t)-b…

This https://arxiv.org/abs/2303.04225 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Feeling Optimistic? Ambiguity Attitudes for Online Decision Making
Due to the complexity of many decision making problems, tree search algorithms often have inadequate information to produce accurate transition models. Robust methods, designed to make safe decisions when faced with these uncertainties, often overlook the impact expressions of uncertainty have on how the decision is made. This work introduces the Ambiguity Attitude Graph Search (AAGS), advocating for more precise representation of ambiguities (uncertainty from a set of plausible models) in deci…