arXiv:2507.06326v1 Announce Type: new Abstract: Deep brain stimulation (DBS) is an established intervention for Parkinson’s disease (PD), but conventional open-loop systems lack adaptability, are energy-inefficient due to continuous stimulation, and provide limited personalization to individual neural dynamics. Adaptive DBS (aDBS) offers a closed-loop alternative, using biomarkers such as beta-band oscillations to dynamically modulate stimulation. While […]

[Submitted on 29 Jun 2025 (v1), last revised 9 Jul 2025 (this version, v2)] View a PDF of the paper titled XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs, by Yitian Gong and 8 other authors View PDF HTML (experimental) Abstract:Speech codecs serve as bridges between speech signals and large language models. An ideal

[Submitted on 24 Jul 2024 (v1), last revised 9 Jul 2025 (this version, v2)] View a PDF of the paper titled Self-Calibrated Variance-Stabilizing Transformations for Real-World Image Denoising, by S\’ebastien Herbreteau and Michael Unser View PDF HTML (experimental) Abstract:Supervised deep learning has become the method of choice for image denoising. It involves the training of

[Submitted on 26 Jun 2025 (v1), last revised 8 Jul 2025 (this version, v2)] View a PDF of the paper titled Wild refitting for black box prediction, by Martin J. Wainwright View PDF HTML (experimental) Abstract:We describe and analyze a computionally efficient refitting procedure for computing high-probability upper bounds on the instance-wise mean-squared prediction error

arXiv:2507.06968v1 Announce Type: cross Abstract: Instruction tuning has become a foundation for unlocking the capabilities of large-scale pretrained models and improving their performance on complex tasks. Thus, the construction of high-quality instruction datasets is crucial for enhancing model performance and generalizability. Although current instruction datasets have reached tens of millions of samples, models finetuned on

[Submitted on 6 Feb 2024 (v1), last revised 9 Jul 2025 (this version, v5)] View a PDF of the paper titled QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning, by Haoxuan Wang and 5 other authors View PDF HTML (experimental) Abstract:The practical deployment of diffusion models is still hindered by the high memory and

arXiv:2507.07066v1 Announce Type: cross Abstract: Acoustic mapping techniques have long been used in spatial audio processing for direction of arrival estimation (DoAE). Traditional beamforming methods for acoustic mapping, while interpretable, often rely on iterative solvers that can be computationally intensive and sensitive to acoustic variability. On the other hand, recent supervised deep learning approaches offer

[Submitted on 5 Mar 2025 (v1), last revised 9 Jul 2025 (this version, v2)] View a PDF of the paper titled AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model, by Wenlun Zhang and Yunshan Zhong and Shimpei Ando and Kentaro Yoshioka View PDF HTML (experimental) Abstract:The Segment Anything Model (SAM) has demonstrated strong

Relational databases constitute the main bulk of enterprise data formats and power many prediction services across Google as well as other services people use every day, like content recommendation or traffic prediction. Most non-trivial applications employ multiple tables — in fact, some elaborate applications at Google might require maintaining hundreds of tables — and extracting

What follows is a fairly loose and basically unfounded hypothesis drawing together simulator theory and optimization demons into something which might help people orient towards what’s going on in reasoning models. It probably also has some relevance to . TL;DR Models trained with guess-and-check on-policy RL, might contain “gremlins”. A gremlin is a circuit (or