Tootfinder

TRACE: Contrastive learning for multi-trial time-series data in neuroscience
Lisa Schmors, Dominic Gonschorek, Jan Niklas B\"ohm, Yongrong Qiu, Na Zhou, Dmitry Kobak, Andreas Tolias, Fabian Sinz, Jacob Reimer, Katrin Franke, Sebastian Damrich, Philipp Berens
https://arxiv.org/abs/2506.04906

TRACE: Contrastive learning for multi-trial time-series data in neuroscience
Modern neural recording techniques such as two-photon imaging allow to acquire vast time-series datasets with responses of hundreds or thousands of neurons. Contrastive learning is a powerful self-supervised framework for learning representations of complex datasets. Existing applications for neural time series rely on generic data augmentations and do not exploit the multi-trial data structure inherent in many neural datasets. Here we present TRACE, a new contrastive learning framework that av…

ONLINE WORKSHOP> Navigating Indra’s Net: Digital Approaches to Text Reuse-based Inter-textuality in Pre-Modern East Asian Texts
https://ift.tt/ajGgrIY
When did aliens become a problem? The Mediterranean Association for Marine Biology and Oceanology in…
via Input 4 RELCFP

This https://arxiv.org/abs/2504.12483 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Beta function without UV divergences
In this paper, we construct the beta function in the functorial formulation of two-dimensional quantum field theories (FQFT). A key feature of this approach is the absence of ultraviolet divergences. We show that, nevertheless, in the FQFT perturbation theory, the local observables of deformed theories acquire logarithmic dimension, leading to a conformal anomaly. The beta function arises in the functorial approach as an infinitesimal transformation of the partition function under the variation…

🇺🇦 #NowPlaying on KEXP's #ElSonido
La Muchacha:
🎵 No azara
#LaMuchacha
https://in-correcto.bandcamp.com/track/in-correcto-070-no-azara
https://open.spotify.com/track/4uIOcEPajm9DLUVZJnLFOO

« “I have read and agree to the Terms” is the biggest lie on the web. Together, we can fix that.»
This reminds me of how for openSNP we used to say that our ToS are “human-readable instead of being lawyer-readable”.
This collaborative effort tries to do the same for many large online services.
https://tosdr.org/en/

NAVER LABS Europe Submission to the Instruction-following Track
Beomseok Lee, Marcely Zanon Boito, Laurent Besacier, Ioan Calapodescu
https://arxiv.org/abs/2506.01808

NAVER LABS Europe Submission to the Instruction-following Track
In this paper we describe NAVER LABS Europe submission to the instruction-following speech processing short track at IWSLT 2025. We participate in the constrained settings, developing systems that can simultaneously perform ASR, ST, and SQA tasks from English speech input into the following target languages: Chinese, Italian, and German. Our solution leverages two pretrained modules: (1) a speech-to-LLM embedding projector trained using representations from the SeamlessM4T-v2-large speech encod…

🇺🇦 #NowPlaying on #BBC6Music's #CraigCharles
The Vines:
🎵 Get Free
#TheVines
https://chazfuego.bandcamp.com/track/major-lazer-get-free-chaz-fuego-remix
https://open.spotify.com/track/1JcGNoiwifg0MdJMVgJQYx

Grapheme-Coherent Phonemic and Prosodic Annotation of Speech by Implicit and Explicit Grapheme Conditioning
Hien Ohnaka, Yuma Shirahata, Byeongseon Park, Ryuichi Yamamoto
https://arxiv.org/abs/2506.04527

Grapheme-Coherent Phonemic and Prosodic Annotation of Speech by Implicit and Explicit Grapheme Conditioning
We propose a model to obtain phonemic and prosodic labels of speech that are coherent with graphemes. Unlike previous methods that simply fine-tune a pre-trained ASR model with the labels, the proposed model conditions the label generation on corresponding graphemes by two methods: 1) Add implicit grapheme conditioning through prompt encoder using pre-trained BERT features. 2) Explicitly prune the label hypotheses inconsistent with the grapheme during inference. These methods enable obtaining p…

This https://arxiv.org/abs/2501.15056 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Feedback-Aware Monte Carlo Tree Search for Efficient Information Seeking in Goal-Oriented Conversations
Effective decision-making and problem-solving in conversational systems require the ability to identify and acquire missing information through targeted questioning. A key challenge lies in efficiently narrowing down a large space of possible outcomes by posing questions that minimize uncertainty. To address this, we introduce a novel framework that leverages Large Language Models (LLMs) to generate information-seeking questions, with Monte Carlo Tree Search (MCTS) to strategically select quest…

Predicting Empirical AI Research Outcomes with Language Models
Jiaxin Wen, Chenglei Si, Yueh-han Chen, He He, Shi Feng
https://arxiv.org/abs/2506.00794 htt…

Predicting Empirical AI Research Outcomes with Language Models
Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial for accelerating empirical AI research, a skill that even expert researchers can only acquire through substantial experience. We build the first benchmark for this task and compare LMs with human experts. Concretely, given two research ideas (e.g., two jailbreaking methods), we aim to predict which will perform better…