Tootfinder

This https://arxiv.org/abs/2503.02769 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training
Recent advancements in speech large language models (SpeechLLMs) have attracted considerable attention. Nonetheless, current methods exhibit suboptimal performance in adhering to speech instructions. Notably, the intelligence of models significantly diminishes when processing speech-form input as compared to direct text-form input. Prior work has attempted to mitigate this semantic inconsistency between speech and text representations through techniques such as representation and behavior align…

My Mac ran out of disk space (1 TB). Which felt … a bit weird and unexpected. So I opened up GrandPerspective to have a look…
Oh wait, what’s that?
/Users/matthiasott/Library/Caches/Adobe/AfterEffects is taking up how much space?
317G?!? 😅
That’s a lot of cache!

Researchers uncover cause of uranium groundwater contamination #environment

Researchers uncover cause of uranium groundwater contamination
A new study published in the journal Environmental Science & Technology and led by researchers at Columbia University Mailman School of Public Health identifies the hidden geological mechanisms behind widespread uranium contamination in Eastern Karnataka, India, where 78% of tested groundwater exceeds safe drinking limits for uranium, and some groundwater uranium contamination reaches levels 75 times the U.S. EPA limit. Uranium exposure can affect the kidneys, bones, and the liver, yet contamin…

This https://arxiv.org/abs/2408.05663 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Physics-informed spectral approximation of Koopman operators
Koopman operators and transfer operators represent nonlinear dynamics in state space through its induced action on linear spaces of observables and measures, respectively. This framework enables the use of linear operator theory for supervised and unsupervised learning of nonlinear dynamical systems, and has received considerable interest in recent years. Here, we propose a data-driven technique for spectral approximation of Koopman operators of continuous-time, measure-preserving ergodic syste…

Posterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancement
Mostafa Sadeghi (MULTISPEECH), Jean-Eudes Ayilo (MULTISPEECH), Romain Serizel (MULTISPEECH), Xavier Alameda-Pineda (ROBOTLEARN)
https://arxiv.org/abs/2507.02391

Posterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancement
We explore unsupervised speech enhancement using diffusion models as expressive generative priors for clean speech. Existing approaches guide the reverse diffusion process using noisy speech through an approximate, noise-perturbed likelihood score, combined with the unconditional score via a trade-off hyperparameter. In this work, we propose two alternative algorithms that directly model the conditional reverse transition distribution of diffusion states. The first method integrates the diffusi…

Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech
Karl El Hajal, Enno Hermann, Sevada Hovsepyan, Mathew Magimai. -Doss
https://arxiv.org/abs/2506.01618 …

Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech
Automatic speech recognition (ASR) systems struggle with dysarthric speech due to high inter-speaker variability and slow speaking rates. To address this, we explore dysarthric-to-healthy speech conversion for improved ASR performance. Our approach extends the Rhythm and Voice (RnV) conversion framework by introducing a syllable-based rhythm modeling method suited for dysarthric speech. We assess its impact on ASR by training LF-MMI models and fine-tuning Whisper on converted speech. Experiment…

SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model
Zhao Yang, Jiwei Zhu, Bing Su
https://arxiv.org/abs/2506.01833 https://

SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model
Inspired by the success of unsupervised pre-training paradigms, researchers have applied these approaches to DNA pre-training. However, we argue that these approaches alone yield suboptimal results because pure DNA sequences lack sufficient information, since their functions are regulated by genomic profiles like chromatin accessibility. Here, we demonstrate that supervised training for genomic profile prediction serves as a more effective alternative to pure sequence pre-training. Furthermore,…

Unsupervised Sparse Coding-based Spiking Neural Network for Real-time Spike Sorting
Alexis Melot, Sean U. N. Wood, Yannick Coffinier, Pierre Yger, Fabien Alibart
https://arxiv.org/abs/2506.24041

Unsupervised Sparse Coding-based Spiking Neural Network for Real-time Spike Sorting
Spike sorting is a crucial step in decoding multichannel extracellular neural signals, enabling the identification of individual neuronal activity. A key challenge in brain-machine interfaces (BMIs) is achieving real-time, low-power spike sorting at the edge while keeping high neural decoding performance. This study introduces the Neuromorphic Sparse Sorter (NSS), a compact two-layer spiking neural network optimized for efficient spike sorting. NSS leverages the Locally Competitive Algorithm (L…

Researchers tested 200 toddlers — 96 chemicals were lurking in their bodies #UnitedStates

Researchers tested 200 toddlers — 96 chemicals were lurking in their bodies
Researchers testing urine from 2- to 4-year-olds in four U.S. states uncovered 96 different chemicals, many of them unmonitored and linked to hormone and brain disruption. Legacy toxins like triclosan are slowly declining, yet replacements such as DINCH plasticizer and modern pesticides are rising. Toddlers—especially the youngest, later-born, and those from minority groups—often carried higher levels than their own mothers. Scientists urge expanded biomonitoring and stricter regulations be…

Understanding and Improving Length Generalization in Recurrent Models
Ricardo Buitrago Ruiz, Albert Gu
https://arxiv.org/abs/2507.02782 https://

Understanding and Improving Length Generalization in Recurrent Models
Recently, recurrent models such as state space models and linear attention have become popular due to their linear complexity in the sequence length. Thanks to their recurrent nature, in principle they can process arbitrarily long sequences, but their performance sometimes drops considerably beyond their training context lengths-i.e. they fail to length generalize. In this work, we provide comprehensive empirical and theoretical analysis to support the unexplored states hypothesis, which posits…