Tootfinder

Generating Shakespeare-like text with an n-gram language model is straight forward and quite simple. But, don't expect to much of it. It will not be able to recreate a lost Shakespear play for you ;-) It's merely a parrot, making up well sounding sentences out of fragments of original Shakespeare texts...
#ise2025

Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching
Giacomo Meanti, Thomas Ryckeboer, Michael Arbel, Julien Mairal
https://arxiv.org/abs/2506.14605

Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching
This work addresses image restoration tasks through the lens of inverse problems using unpaired datasets. In contrast to traditional approaches -- which typically assume full knowledge of the forward model or access to paired degraded and ground-truth images -- the proposed method operates under minimal assumptions and relies only on small, unpaired datasets. This makes it particularly well-suited for real-world scenarios, where the forward model is often unknown or misspecified, and collecting…

Looking forward to #IC2S2 next week! On tuesday we'll have a talk on our "Urban highways" PNAS paper, and a poster (ID 94) on 3 bike network papers. See you there!

Dual-Numbers Reverse AD for Functional Array Languages
Tom Smeding, Miko{\l}aj Konarski, Simon Peyton Jones, Andrew Fitzgibbon
https://arxiv.org/abs/2507.12640

Dual-Numbers Reverse AD for Functional Array Languages
The standard dual-numbers construction works well for forward-mode automatic differentiation (AD) and is attractive due to its simplicity; recently, it also has been adapted to reverse-mode AD, but practical performance, especially on array programs, leaves a lot to be desired. In this paper we introduce first-class support for multidimensional arrays in dual-numbers reverse-mode AD with little to no performance overhead. The algorithm consists of three loosely-coupled components: a semantics-p…

SF folks: please call your supervisor and ask them not to redirect permanent affordable housing funds to temporary shelter
it’s likely illegal and it’s nonsense: the shelters would free up if people could exit to permanent housing!
https://dsasf.org/ocoh/

San Francisco is About to Defund Solutions to Homelessness
After a late-night session on June 26, the Budget & Appropriations Committee of San Francisco’s Board of Supervisors is moving forward with a set of proposed resolutions regarding the budget. T…

Explain First, Trust Later: LLM-Augmented Explanations for Graph-Based Crypto Anomaly Detection
Adriana Watson
https://arxiv.org/abs/2506.14933 https://

Explain First, Trust Later: LLM-Augmented Explanations for Graph-Based Crypto Anomaly Detection
The decentralized finance (DeFi) community has grown rapidly in recent years, pushed forward by cryptocurrency enthusiasts interested in the vast untapped potential of new markets. The surge in popularity of cryptocurrency has ushered in a new era of financial crime. Unfortunately, the novelty of the technology makes the task of catching and prosecuting offenders particularly challenging. Thus, it is necessary to implement automated detection tools related to policies to address the growing cri…

A Scalable Hybrid Training Approach for Recurrent Spiking Neural Networks
Maximilian Baronig, Yeganeh Bahariasl, Ozan \"Ozdenizci, Robert Legenstein
https://arxiv.org/abs/2506.14464

A Scalable Hybrid Training Approach for Recurrent Spiking Neural Networks
Recurrent spiking neural networks (RSNNs) can be implemented very efficiently in neuromorphic systems. Nevertheless, training of these models with powerful gradient-based learning algorithms is mostly performed on standard digital hardware using Backpropagation through time (BPTT). However, BPTT has substantial limitations. It does not permit online training and its memory consumption scales linearly with the number of computation steps. In contrast, learning methods using forward propagation o…

Thanks to your incredible support, we've made it to 10.064€ 💙 Our goal is 12,439€ to continue the fight for justice. Every donation matters in pushing this cause ahead. Thank you for standing with us! 🙏 Find out more and donate here: https://chardonsbleus.org/donate

Donate | Association Chardons Bleus
OKC Cult Leader Robert Spatz Faces Renewed Legal Pressure Over Abuse Claims Since 2019, six survivors brought forward allegations of severe abuse, including ...

Hierarchical Rectified Flow Matching with Mini-Batch Couplings
Yichi Zhang, Yici Yan, Alex Schwing, Zhizhen Zhao
https://arxiv.org/abs/2507.13350 https://

Hierarchical Rectified Flow Matching with Mini-Batch Couplings
Flow matching has emerged as a compelling generative modeling approach that is widely used across domains. To generate data via a flow matching model, an ordinary differential equation (ODE) is numerically solved via forward integration of the modeled velocity field. To better capture the multi-modality that is inherent in typical velocity fields, hierarchical flow matching was recently introduced. It uses a hierarchy of ODEs that are numerically integrated when generating data. This hierarchy …