Tootfinder

Learning Neural Networks by Neuron Pursuit
Akshay Kumar, Jarvis Haupt
https://arxiv.org/abs/2509.12154 https://arxiv.org/pdf/2509.12154

Learning Neural Networks by Neuron Pursuit
The first part of this paper studies the evolution of gradient flow for homogeneous neural networks near a class of saddle points exhibiting a sparsity structure. The choice of these saddle points is motivated from previous works on homogeneous networks, which identified the first saddle point encountered by gradient flow after escaping the origin. It is shown here that, when initialized sufficiently close to such saddle points, gradient flow remains near the saddle point for a sufficiently lon…

NeuroStrike: Neuron-Level Attacks on Aligned LLMs
Lichao Wu, Sasha Behrouzi, Mohamadreza Rostami, Maximilian Thang, Stjepan Picek, Ahmad-Reza Sadeghi
https://arxiv.org/abs/2509.11864

NeuroStrike: Neuron-Level Attacks on Aligned LLMs
Safety alignment is critical for the ethical deployment of large language models (LLMs), guiding them to avoid generating harmful or unethical content. Current alignment techniques, such as supervised fine-tuning and reinforcement learning from human feedback, remain fragile and can be bypassed by carefully crafted adversarial prompts. Unfortunately, such attacks rely on trial and error, lack generalizability across models, and are constrained by scalability and reliability. This paper presen…

Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs
Yixiao Zhou, Ziyu Zhao, Dongzhou Cheng, zhiliang wu, Jie Gui, Yi Yang, Fei Wu, Yu Cheng, Hehe Fan
https://arxiv.org/abs/2509.10377

Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs
Sparse Mixture-of-Experts (SMoE) architectures are widely used in large language models (LLMs) due to their computational efficiency. However, though only a few experts are activated for each token, SMoE still requires loading all expert parameters, leading to high memory usage and challenges in deployment. Previous work has tried to reduce the overhead by pruning and merging experts, but primarily focused on expert-level operations, leaving neuron-level structure underexplored. We propose DERN…

fly_larva: Drosophila larva brain (2023)
A complete synaptic map of the brain connectome of the larva of the fruit fly Drosophila melanogaster. Nodes are neurons, and edges are synaptic connections, traced individually from brain image sections using three-dimensional electron microscopy–based reconstruction. Node metadata include the neuron hempisphere, hemispherical homologue, cell type, annotations, and inferred cluster. Edge metadata include the type of interaction (`'aa'`,…

⚡ Team develops high-speed, ultra-low-power superconductive neuron device
#electronics

Team develops high-speed, ultra-low-power superconductive neuron device
A research team has developed a neuron device that holds potential for application in large-scale, high-speed superconductive neural network circuits. The device operates at high speeds with ultra-low-power consumption and is tolerant to parameter fluctuations during circuit fabrication.

Replaced article(s) found for cs.PF. https://arxiv.org/list/cs.PF/new
[1/1]:
- Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking
Tuowei Wang, Ruwen Fan, Minxing Huang, Zixu Hao, Kun Li, Ting Cao, Youyou Lu, Yaoxue Zhang, Ju Ren

Learning Neuron Dynamics within Deep Spiking Neural Networks
Eric Jahns, Davi Moreno, Michel A. Kinsy
https://arxiv.org/abs/2510.07341 https://arxiv.org/pd…

Learning Neuron Dynamics within Deep Spiking Neural Networks
Spiking Neural Networks (SNNs) offer a promising energy-efficient alternative to Artificial Neural Networks (ANNs) by utilizing sparse and asynchronous processing through discrete spike-based computation. However, the performance of deep SNNs remains limited by their reliance on simple neuron models, such as the Leaky Integrate-and-Fire (LIF) model, which cannot capture rich temporal dynamics. While more expressive neuron models exist, they require careful manual tuning of hyperparameters and a…

Impact of Neuron Models on Spiking Neural Networks performance. A Complexity Based Classification Approach
Zofia Rudnicka, Janusz Szczepanski, Agnieszka Pregowska
https://arxiv.org/abs/2509.06970

Impact of Neuron Models on Spiking Neural Networks performance. A Complexity Based Classification Approach
This study explores how the selection of neuron models and learning rules impacts the classification performance of Spiking Neural Networks (SNNs), with a focus on applications in bio-signal processing. We compare biologically inspired neuron models, including Leaky Integrate-and-Fire (LIF), metaneurons, and probabilistic Levy-Baxter (LB) neurons, across multiple learning rules, including spike-timing-dependent plasticity (STDP), tempotron, and reward-modulated updates. A novel element of this …

Utilizing dynamic sparsity on pretrained DETR
Reza Sedghi, Anand Subramoney, David Kappel
https://arxiv.org/abs/2510.09380 https://arxiv.org/pdf/2510.09380…

Utilizing dynamic sparsity on pretrained DETR
Efficient inference with transformer-based models remains a challenge, especially in vision tasks like object detection. We analyze the inherent sparsity in the MLP layers of DETR and introduce two methods to exploit it without retraining. First, we propose Static Indicator-Based Sparsification (SIBS), a heuristic method that predicts neuron inactivity based on fixed activation patterns. While simple, SIBS offers limited gains due to the input-dependent nature of sparsity. To address this, we i…

Replaced article(s) found for cs.OS. https://arxiv.org/list/cs.OS/new
[1/1]:
- Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking
Tuowei Wang, Ruwen Fan, Minxing Huang, Zixu Hao, Kun Li, Ting Cao, Youyou Lu, Yaoxue Zhang, Ju Ren

Optimal monophasic, asymmetric electric field pulses for selective transcranial magnetic stimulation (TMS) with minimised power and coil heating
Ke Ma, Andrey Vlasov, Zeynep B. Simsek, Jinshui Zhang, Yiru Li, Boshuo Wang, David L. K. Murphy, Jessica Y. Choi, Maya E. Clinton, Noreen Bukhari-Parlakturk, Angel V. Peterchev, Stephan M. Goetz
https://

Optimal monophasic, asymmetric electric field pulses for selective transcranial magnetic stimulation (TMS) with minimised power and coil heating
Transcranial magnetic stimulation (TMS) with asymmetric electric field pulses, such as monophasic, offers directional selectivity for neural activation but requires excessive energy. Previous pulse shape optimisation has been limited to symmetric pulses or heavily constrained variations of conventional waveforms without achieving general optimality in energy efficiency or neural selectivity. We implemented an optimisation framework that incorporates neuron model activation constraints and flexi…

Neuron-Level Analysis of Cultural Understanding in Large Language Models
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala, Hitomi Yanaka
https://arxiv.org/abs/2510.08284 https:/…

Neuron-Level Analysis of Cultural Understanding in Large Language Models
As large language models (LLMs) are increasingly deployed worldwide, ensuring their fair and comprehensive cultural understanding is important. However, LLMs exhibit cultural bias and limited awareness of underrepresented cultures, while the mechanisms underlying their cultural understanding remain underexplored. To fill this gap, we conduct a neuron-level analysis to identify neurons that drive cultural behavior, introducing a gradient-based scoring method with additional filtering for precise…

RE: https://mas.to/@seeingwithsound/115510086105712226
Brain-wide single-neuron bases of working memory for sounds in humans

SEPhIA: <1 laser/neuron Spiking Electro-Photonic Integrated Multi-Tiled Architecture for Scalable Optical Neuromorphic Computing
Mat\v{e}j Hejda, Aishwarya Natarajan, Chaerin Hong, Mehmet Berkay On, S\'ebastien d'Herbais de Thun, Raymond G. Beausoleil, Thomas Van Vaerenbergh
https://arxiv.org/abs/2510.07427

SEPhIA: <1 laser/neuron Spiking Electro-Photonic Integrated Multi-Tiled Architecture for Scalable Optical Neuromorphic Computing
Research into optical spiking neural networks (SNNs) has primarily focused on spiking devices, networks of excitable lasers or numerical modelling of large architectures, often overlooking key constraints such as limited optical power, crosstalk and footprint. We introduce SEPhIA, a photonic-electronic, multi-tiled SNN architecture emphasizing implementation feasibility and realistic scaling. SEPhIA leverages microring resonator modulators (MRMs) and multi-wavelength sources to achieve effectiv…

Catwalk: Unary Top-K for Efficient Ramp-No-Leak Neuron Design for Temporal Neural Networks
Devon Lister, Prabhu Vellaisamy, John Paul Shen, Di Wu
https://arxiv.org/abs/2508.21267

Catwalk: Unary Top-K for Efficient Ramp-No-Leak Neuron Design for Temporal Neural Networks
Temporal neural networks (TNNs) are neuromorphic neural networks that utilize bit-serial temporal coding. TNNs are composed of columns, which in turn employ neurons as their building blocks. Each neuron processes volleys of input spikes, modulated by associated synaptic weights, on its dendritic inputs. Recently proposed neuron implementation in CMOS employs a Spike Response Model (SRM) with a ramp-no-leak (RNL) response function and assumes all the inputs can carry spikes. However, in actual s…

cintestinalis: Tadpole larva brain (C. intestinalis)
Entire connectivity matrix for the complete brain of a larva of Ciona intestinalis. Each directed edge represents a synaptic connection from pre-synaptic cell i to post-synaptic cell j (may not be a neuron). Edge weights represent the cumulative depth of presynaptic contacts in µm.
This network has 205 nodes and 2903 edges.
Tags: Biological, Connectome, Weighted

Associative Memory Model with Neural Networks: Memorizing multiple images with one neuron
Hiroshi Inazawa
https://arxiv.org/abs/2510.06542 https://arxiv.or…

Associative Memory Model with Neural Networks: Memorizing multiple images with one neuron
This paper presents a neural network model (associative memory model) for memory and recall of images. In this model, only a single neuron can memorize multi-images and when that neuron is activated, it is possible to recall all the memorized images at the same time. The system is composed of a single cluster of numerous neurons, referred to as the "Cue Ball," and multiple neural network layers, collectively called the "Recall Net." One of the features of this model is that several different im…

Replaced article(s) found for q-bio.NC. https://arxiv.org/list/q-bio.NC/new
[1/1]:
- Auditory steady-state response and gamma oscillations in an excitatory-inhibitory balanced neuron...
Duoyu Feng, Jiajia Li

Replaced article(s) found for cs.PF. https://arxiv.org/list/cs.PF/new
[1/1]:
- Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking
Tuowei Wang, Ruwen Fan, Minxing Huang, Zixu Hao, Kun Li, Ting Cao, Youyou Lu, Yaoxue Zhang, Ju Ren

Field Free Spin-Orbit Torque Controlled Synapse and Stochastic Neuron Devices for Spintronic Boltzmann Neural Networks
Aijaz H. Lone, Meng Tang, Camelia Florica, Bin He, Jingkai Xu, Xixiang Zhang, Gianluca Setti
https://arxiv.org/abs/2510.05616

Field Free Spin-Orbit Torque Controlled Synapse and Stochastic Neuron Devices for Spintronic Boltzmann Neural Networks
Spintronics offers a promising approach to energy efficient neuromorphic computing by integrating the functionalities of synapses and neurons within a single platform. A major challenge, however, is achieving field-free spin orbit torque SOT control over both synaptic and neuronal devices using an industry-adopted spintronic materials stack. In this study, we present field-free SOT spintronic synapses utilizing a CoFeB ferromagnetic thin film system, where asymmetrical device design and specifi…

A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion Models
Qinqin He, Jiaqi Weng, Jialing Tao, Hui Xue
https://arxiv.org/abs/2509.21008 https://

A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion Models
Text-to-image models exhibit remarkable capabilities in image generation. However, they also pose safety risks of generating harmful content. A key challenge of existing concept erasure methods is the precise removal of target concepts while minimizing degradation of image quality. In this paper, we propose Single Neuron-based Concept Erasure (SNCE), a novel approach that can precisely prevent harmful content generation by manipulating only a single neuron. Specifically, we train a Sparse Autoe…

fly_larva: Drosophila larva brain (2023)
A complete synaptic map of the brain connectome of the larva of the fruit fly Drosophila melanogaster. Nodes are neurons, and edges are synaptic connections, traced individually from brain image sections using three-dimensional electron microscopy–based reconstruction. Node metadata include the neuron hempisphere, hemispherical homologue, cell type, annotations, and inferred cluster. Edge metadata include the type of interaction (`'aa'`,…

Minimal Neuron Circuits: Bursters
Amr Nabil, T. Nandha Kumar, Haider Abbas F. Almurib
https://arxiv.org/abs/2509.17731 https://arxiv.org/pdf/2509.17731

Minimal Neuron Circuits: Bursters
This work introduces a novel methodology for designing biologically plausible bursting neuron circuits using a minimal number of components. We hypothesize that to design circuits capable of bursting, the neuron circuit design must mimic a neuron model that inherently exhibits bursting dynamics. Consequently, classical models such as the Hodgkin-Huxley, $I_{Na,p}+I_{K}$, and FitzHugh-Nagumo models are not suitable choices. Instead, we propose a methodology for designing neuron circuits that emu…

Crosslisted article(s) found for physics.optics. https://arxiv.org/list/physics.optics/new
[1/1]:
- SEPhIA: <1 laser/neuron Spiking Electro-Photonic Integrated Multi-Tiled Architecture for Scalable...
Hejda, Natarajan, Hong, On, de Thun, Beausoleil, Van Vaerenbergh
…

How AI tools from ElevenLabs and others were used to recreate a woman's voice, lost to motor neuron disease, from just eight seconds of audio on a VHS tape (Beth Rose/BBC)
https://www.bbc.com/news/articles/c1ejvxne7elo

How eight seconds of scratchy audio from a VHS tape gave a mum back her voice
Sarah Ezekiel was 34 with two children when motor neurone disease took away her ability to speak.

High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization
Masih Aminbeidokhti, Heitor Rapela Medeiros, Eric Granger, Marco Pedersoli
https://arxiv.org/abs/2510.06955 …

High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization
Ensembling fine-tuned models initialized from powerful pre-trained weights is a common strategy to improve robustness under distribution shifts, but it comes with substantial computational costs due to the need to train and store multiple models. Dropout offers a lightweight alternative by simulating ensembles through random neuron deactivation; however, when applied to pre-trained models, it tends to over-regularize and disrupt critical representations necessary for generalization. In this wor…

cintestinalis: Tadpole larva brain (C. intestinalis)
Entire connectivity matrix for the complete brain of a larva of Ciona intestinalis. Each directed edge represents a synaptic connection from pre-synaptic cell i to post-synaptic cell j (may not be a neuron). Edge weights represent the cumulative depth of presynaptic contacts in µm.
This network has 205 nodes and 2903 edges.
Tags: Biological, Connectome, Weighted

Deep Complex-valued Neural-Network Modeling and Optimization of Stacked Intelligent Surfaces
Abdullah Zayat, Omran Abbas, Loic Markley, Anas Chaaban
https://arxiv.org/abs/2509.00340

Deep Complex-valued Neural-Network Modeling and Optimization of Stacked Intelligent Surfaces
We propose a complex-valued neural-network (CV-NN) framework to optimally configure stacked intelligent surfaces (SIS) in next-generation multi-antenna systems. Unlike conventional solutions that separately tune analog metasurface phases or rely strictly on SVD-based orthogonal decompositions, our method models each SIS element as a unit-modulus complex-velued neuron in an end-to-end differentiable pipeline. This approach avoids enforcing channel orthogonality and instead allows for richer wave…

Analysis of a mean-field limit of interacting two-dimensional nonlinear integrate-and-fire neurons
Romain Veltz
https://arxiv.org/abs/2508.19134 https://ar…

Analysis of a mean-field limit of interacting two-dimensional nonlinear integrate-and-fire neurons
We study the solutions of a McKean-Vlasov stochastic differential equation (SDE) driven by a Poisson process. In neuroscience, this SDE models the mean field limit of a system of $N$ interacting excitatory neurons with $N$ large. Each neuron spikes randomly with rate depending on its membrane potential. At each spiking time, the neuron potential is reset to the value $\bar v$, its adaptation variable is incremented by $\bar w$ and all other neurons receive an additional amount $J/N$ of pote…

Crosslisted article(s) found for cs.SE. https://arxiv.org/list/cs.SE/new
[1/1]:
- Prophecy: Inferring Formal Properties from Neuron Activations
Divya Gopinath, Corina S. Pasareanu, Muhammad Usman

Mean-field analysis of a neural network with stochastic STDP
Pascal Helson, Etienne Tanr\'e, Romain Veltz
https://arxiv.org/abs/2510.02545 https://arxi…

Mean-field analysis of a neural network with stochastic STDP
Analysing biological spiking neural network models with synaptic plasticity has proven to be challenging both theoretically and numerically. In a network with N all-to-all connected neurons, the number of synaptic connections is on the order of $N^2$, making these models computationally demanding. Furthermore, the intricate coupling between neuron and synapse dynamics, along with the heterogeneity generated by plasticity, hinder the use of classic theoretical tools such as mean-field or slow-fa…

Weight Mapping Properties of a Dual Tree Single Clock Adiabatic Capacitive Neuron
Mike Smart, Sachin Maheshwari, Himadri Singh Raghav, Alexander Serb
https://arxiv.org/abs/2509.18143

Weight Mapping Properties of a Dual Tree Single Clock Adiabatic Capacitive Neuron
Dual Tree Single Clock (DTSC) Adiabatic Capacitive Neuron (ACN) circuits offer the potential for highly energy-efficient Artificial Neural Network (ANN) computation in full custom analog IC designs. The efficient mapping of Artificial Neuron (AN) abstract weights, extracted from the software-trained ANNs, onto physical ACN capacitance values has, however, yet to be fully researched. In this paper, we explore the unexpected hidden complexities, challenges and properties of the mapping, as well a…

Learning Internal Biological Neuron Parameters and Complexity-Based Encoding for Improved Spiking Neural Networks Performance
Zofia Rudnicka, Janusz Szczepanski, Agnieszka Pregowska
https://arxiv.org/abs/2508.11674

Learning Internal Biological Neuron Parameters and Complexity-Based Encoding for Improved Spiking Neural Networks Performance
This study introduces a novel approach by replacing the traditional perceptron neuron model with a biologically inspired probabilistic meta neuron, where the internal neuron parameters are jointly learned, leading to improved classification accuracy of spiking neural networks (SNNs). To validate this innovation, we implement and compare two SNN architectures: one based on standard leaky integrate-and-fire (LIF) neurons and another utilizing the proposed probabilistic meta neuron model. As a sec…

cintestinalis: Tadpole larva brain (C. intestinalis)
Entire connectivity matrix for the complete brain of a larva of Ciona intestinalis. Each directed edge represents a synaptic connection from pre-synaptic cell i to post-synaptic cell j (may not be a neuron). Edge weights represent the cumulative depth of presynaptic contacts in µm.
This network has 205 nodes and 2903 edges.
Tags: Biological, Connectome, Weighted

Crosslisted article(s) found for cs.DC. https://arxiv.org/list/cs.DC/new
[1/1]:
- DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction
Weilin Cai, Le Qin, Shwai He, Junwei Cui, Ang Li, Jiayi Huang

🎛️ A new system can dial expression of synthetic genes up or down
#molbio

A new system can dial expression of synthetic genes up or down
For decades, synthetic biologists have been developing gene circuits that can be transferred into cells for applications such as reprogramming a stem cell into a neuron or generating a protein that could help treat a disease such as fragile X syndrome.

Superposition disentanglement of neural representations reveals hidden alignment
Andr\'e Longon, David Klindt, Meenakshi Khosla
https://arxiv.org/abs/2510.03186 https://

Superposition disentanglement of neural representations reveals hidden alignment
The superposition hypothesis states that a single neuron within a population may participate in the representation of multiple features in order for the population to represent more features than the number of neurons. In neuroscience and AI, representational alignment metrics measure the extent to which different deep neural networks (DNNs) or brains represent similar information. In this work, we explore a critical question: \textit{does superposition interact with alignment metrics in any un…

Memristor-Driven Spike Encoding for Fully Implantable Cochlear Implants
T\'imea N\'ora T\"or\"ok, Roland K\"ovecs, Ferenc Braun, Zsigmond Pollner, Tam\'as Zeffer, Nguyen Quoc Kh\'anh, L\'aszl\'o P\'osa, P\'eter R\'ev\'esz, Heungsoo Kim, Alberto Piqu\'e, Andr\'as Halbritter, J\'anos Volk
https://…

Memristor-Driven Spike Encoding for Fully Implantable Cochlear Implants
Neurodynamic behavior of artificial neuron circuits made of Mott memristors provides versatile opportunities to utilize them for artificial sensing. Their small size and energy efficiency of generating spiking electrical signals enable usage in fully implantable cochlear implants. Here, we propose an auditory sensing unit realized by a piezo-MEMS (micro-electromechanical systems) cantilever connected to a VO$_2$ nanogap Mott memristor-based oscillator circuit. This auditory sensing unit is capa…

Crosslisted article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/1]:
- Weight Mapping Properties of a Dual Tree Single Clock Adiabatic Capacitive Neuron
Mike Smart, Sachin Maheshwari, Himadri Singh Raghav, Alexander Serb

cintestinalis: Tadpole larva brain (C. intestinalis)
Entire connectivity matrix for the complete brain of a larva of Ciona intestinalis. Each directed edge represents a synaptic connection from pre-synaptic cell i to post-synaptic cell j (may not be a neuron). Edge weights represent the cumulative depth of presynaptic contacts in µm.
This network has 205 nodes and 2903 edges.
Tags: Biological, Connectome, Weighted

The Impact of Structural Changes on Learning Capacity in the Fly Olfactory Neural Circuit
Katherine Xie, Gabriel Koch Ocker
https://arxiv.org/abs/2509.19351 https://

The Impact of Structural Changes on Learning Capacity in the Fly Olfactory Neural Circuit
The Drosophila mushroom body (MB) is known to be involved in olfactory learning and memory; the synaptic plasticity of the Kenyon cell (KC) to mushroom body output neuron (MBON) synapses plays a key role in the learning process. Previous research has focused on projection neuron (PN) to Kenyon cell (KC) connectivity within the MB; we examine how perturbations to the mushroom body circuit structure and changes in connectivity, specifically within the KC to mushroom body output neuron (MBON) neur…

fly_larva: Drosophila larva brain (2023)
A complete synaptic map of the brain connectome of the larva of the fruit fly Drosophila melanogaster. Nodes are neurons, and edges are synaptic connections, traced individually from brain image sections using three-dimensional electron microscopy–based reconstruction. Node metadata include the neuron hempisphere, hemispherical homologue, cell type, annotations, and inferred cluster. Edge metadata include the type of interaction (`'aa'`,…

Energy-Regularized Sequential Model Editing on Hyperspheres
Qingyuan Liu, Jia-Chen Gu, Yunzhi Yao, Hong Wang, Nanyun Peng
https://arxiv.org/abs/2510.01172 https://

Energy-Regularized Sequential Model Editing on Hyperspheres
Large language models (LLMs) require constant updates to remain aligned with evolving real-world knowledge. Model editing offers a lightweight alternative to retraining, but sequential editing often destabilizes representations and induces catastrophic forgetting. In this work, we seek to better understand and mitigate performance degradation caused by sequential editing. We hypothesize that hyperspherical uniformity, a property that maintains uniform distribution of neuron weights on a hypersp…

Nambu Non-equilibrium Thermodynamics III: Application to specific phenomena
So Katagiri, Yoshiki Matsuoka, Akio Sugamoto
https://arxiv.org/abs/2509.12641 https://

Nambu Non-equilibrium Thermodynamics III: Application to specific phenomena
We apply Nambu non-equilibrium thermodynamics (NNET)-a dynamics with multiple Hamiltonians coupled to entropy-induced dissipation-to paradigmatic far-from-equilibrium systems. Concretely, we construct NNET realizations for the Belousov-Zhabotinsky (BZ) reaction (oscillatory), the Hindmarsh-Rose neuron model (spiking), and the Lorenz and Chen systems (chaotic), and analyze their dynamical and thermodynamic signatures. Across all cases the velocity field cleanly decomposes into a reversible Nambu…

NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
Xiaohan Bi, Binhang Qi, Hailong Sun, Xiang Gao, Yue Yu, Xiaojun Liang
https://arxiv.org/abs/2508.11348

NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
With the growing incorporation of deep neural network (DNN) models into modern software systems, the prohibitive construction costs have become a significant challenge. Model reuse has been widely applied to reduce training costs, but indiscriminately reusing entire models may incur significant inference overhead. Consequently, DNN modularization has gained attention, enabling module reuse by decomposing DNN models. The emerging modularizing-while-training (MwT) paradigm, which incorporates mod…

Musculoskeletal simulation of limb movement biomechanics in Drosophila melanogaster
Pembe Gizem \"Ozdil, Chuanfang Ning, Jasper S. Phelps, Sibo Wang-Chen, Guy Elisha, Alexander Blanke, Auke Ijspeert, Pavan Ramdya
https://arxiv.org/abs/2509.06426

Musculoskeletal simulation of limb movement biomechanics in Drosophila melanogaster
Computational models are critical to advance our understanding of how neural, biomechanical, and physical systems interact to orchestrate animal behaviors. Despite the availability of near-complete reconstructions of the Drosophila melanogaster central nervous system, musculature, and exoskeleton, anatomically and physically grounded models of fly leg muscles are still missing. These models provide an indispensable bridge between motor neuron activity and joint movements. Here, we introduce the…

fly_larva: Drosophila larva brain (2023)
A complete synaptic map of the brain connectome of the larva of the fruit fly Drosophila melanogaster. Nodes are neurons, and edges are synaptic connections, traced individually from brain image sections using three-dimensional electron microscopy–based reconstruction. Node metadata include the neuron hempisphere, hemispherical homologue, cell type, annotations, and inferred cluster. Edge metadata include the type of interaction (`'aa'`,…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[4/4]:
- Interpreting ResNet-based CLIP via Neuron-Attention Decomposition
Edmund Bu, Yossi Gandelsman

Continual Personalization for Diffusion Models
Yu-Chien Liao, Jr-Jen Chen, Chi-Pin Huang, Ci-Siang Lin, Meng-Lin Wu, Yu-Chiang Frank Wang
https://arxiv.org/abs/2510.02296 https:…

Continual Personalization for Diffusion Models
Updating diffusion models in an incremental setting would be practical in real-world applications yet computationally challenging. We present a novel learning strategy of Concept Neuron Selection (CNS), a simple yet effective approach to perform personalization in a continual learning scheme. CNS uniquely identifies neurons in diffusion models that are closely related to the target concepts. In order to mitigate catastrophic forgetting problems while preserving zero-shot text-to-image generatio…

fly_larva: Drosophila larva brain (2023)
A complete synaptic map of the brain connectome of the larva of the fruit fly Drosophila melanogaster. Nodes are neurons, and edges are synaptic connections, traced individually from brain image sections using three-dimensional electron microscopy–based reconstruction. Node metadata include the neuron hempisphere, hemispherical homologue, cell type, annotations, and inferred cluster. Edge metadata include the type of interaction (`'aa'`,…

IzhiRISC-V -- a RISC-V-based Processor with Custom ISA Extension for Spiking Neuron Networks Processing with Izhikevich Neurons
Wiktor J. Szczerek, Artur Podobas
https://arxiv.org/abs/2508.12846

IzhiRISC-V -- a RISC-V-based Processor with Custom ISA Extension for Spiking Neuron Networks Processing with Izhikevich Neurons
Spiking Neural Network processing promises to provide high energy efficiency due to the sparsity of the spiking events. However, when realized on general-purpose hardware -- such as a RISC-V processor -- this promise can be undermined and overshadowed by the inefficient code, stemming from repeated usage of basic instructions for updating all the neurons in the network. One of the possible solutions to this issue is the introduction of a custom ISA extension with neuromorphic instructions for s…

Meta-optical Miniscope for Multifunctional Imaging
Zhihao Zhou, Khushboo Kumari, Ningzhi Xie, Shane Colburn, Chetan Poudel, Praneeth Chakravarthula, Karl F. B\"ohringer, Arka Majumdar, Johannes E. Fr\"och
https://arxiv.org/abs/2509.16373

Meta-optical Miniscope for Multifunctional Imaging
Miniaturized microscopes (miniscopes) have opened a new frontier in animal behavior studies, enabling real-time imaging of neuron activity while leaving animals largely unconstrained. Canonical designs typically use Gradient-Index (GRIN) lenses or refractive lenses as the objective module for excitation and fluorescence collection, but GRIN lenses suffer from aberrations and refractive lenses are bulky and complex. Meta-optics, composed of subwavelength diffractive elements, offer a promising a…

Optimal rate-variance coding due to firing threshold adaptation near criticality
Mauricio Girardi-Schappo, Leonard Maler, Andr\'e Longtin
https://arxiv.org/abs/2509.04106 ht…

Optimal rate-variance coding due to firing threshold adaptation near criticality
Recurrently connected neuron populations play key roles in sensory perception and memory storage across various brain regions. While these populations are often assumed to encode information through firing rates, this method becomes unreliable with weak stimuli. We propose that in such cases, information can be transmitted via spatial spike patterns, employing a sparse or combinatorial coding based on firing rate variance. Around the critical point of a stochastic recurrent excitable network, w…

Replaced article(s) found for q-bio.TO. https://arxiv.org/list/q-bio.TO/new
[1/1]:
- Revisiting convolutive blind source separation for identifying spiking motor neuron activity: Fro...
Thomas Klotz, Robin Rohl\'en

Incorporating the Refractory Period into Spiking Neural Networks through Spike-Triggered Threshold Dynamics
Yang Li, Xinyi Zeng, Zhe Xue, Pinxian Zeng, Zikai Zhang, Yan Wang
https://arxiv.org/abs/2509.17769

Incorporating the Refractory Period into Spiking Neural Networks through Spike-Triggered Threshold Dynamics
As the third generation of neural networks, spiking neural networks (SNNs) have recently gained widespread attention for their biological plausibility, energy efficiency, and effectiveness in processing neuromorphic datasets. To better emulate biological neurons, various models such as Integrate-and-Fire (IF) and Leaky Integrate-and-Fire (LIF) have been widely adopted in SNNs. However, these neuron models overlook the refractory period, a fundamental characteristic of biological neurons. Resear…

fly_larva: Drosophila larva brain (2023)
A complete synaptic map of the brain connectome of the larva of the fruit fly Drosophila melanogaster. Nodes are neurons, and edges are synaptic connections, traced individually from brain image sections using three-dimensional electron microscopy–based reconstruction. Node metadata include the neuron hempisphere, hemispherical homologue, cell type, annotations, and inferred cluster. Edge metadata include the type of interaction (`'aa'`,…

SDSNN: A Single-Timestep Spiking Neural Network with Self-Dropping Neuron and Bayesian Optimization
Changqing Xu, Buxuan Song, Yi Liu, Xinfang Liao, Wenbin Zheng, Yintang Yang
https://arxiv.org/abs/2508.10913

SDSNN: A Single-Timestep Spiking Neural Network with Self-Dropping Neuron and Bayesian Optimization
Spiking Neural Networks (SNNs), as an emerging biologically inspired computational model, demonstrate significant energy efficiency advantages due to their event-driven information processing mechanism. Compared to traditional Artificial Neural Networks (ANNs), SNNs transmit information through discrete spike signals, which substantially reduces computational energy consumption through their sparse encoding approach. However, the multi-timestep computation model significantly increases inferenc…

fly_larva: Drosophila larva brain (2023)
A complete synaptic map of the brain connectome of the larva of the fruit fly Drosophila melanogaster. Nodes are neurons, and edges are synaptic connections, traced individually from brain image sections using three-dimensional electron microscopy–based reconstruction. Node metadata include the neuron hempisphere, hemispherical homologue, cell type, annotations, and inferred cluster. Edge metadata include the type of interaction (`'aa'`,…

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
Zhuoxuan Zhang, Jinhao Duan, Edward Kim, Kaidi Xu
https://arxiv.org/abs/2509.13664 https://

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
Ambiguity is pervasive in real-world questions, yet large language models (LLMs) often respond with confident answers rather than seeking clarification. In this work, we show that question ambiguity is linearly encoded in the internal representations of LLMs and can be both detected and controlled at the neuron level. During the model's pre-filling stage, we identify that a small number of neurons, as few as one, encode question ambiguity information. Probes trained on these Ambiguity-Encoding …

Fast reconstruction of degenerate populations of conductance-based neuron models from spike times
Julien Brandoit, Damien Ernst, Guillaume Drion, Arthur Fyon
https://arxiv.org/abs/2509.12783

Fast reconstruction of degenerate populations of conductance-based neuron models from spike times
Neurons communicate through spikes, and spike timing is a crucial part of neuronal processing. Spike times can be recorded experimentally both intracellularly and extracellularly, and are the main output of state-of-the-art neural probes. On the other hand, neuronal activity is controlled at the molecular level by the currents generated by many different transmembrane proteins called ion channels. Connecting spike timing to ion channel composition remains an arduous task to date. To address thi…

Crosslisted article(s) found for cs.NE. https://arxiv.org/list/cs.NE/new
[1/1]:
- Catwalk: Unary Top-K for Efficient Ramp-No-Leak Neuron Design for Temporal Neural Networks
Devon Lister, Prabhu Vellaisamy, John Paul Shen, Di Wu

Benchmarking spike source localization algorithms in high density probes
Hao Zhao, Xinhe Zhang, Arnau Marin-Llobet, Xinyi Lin, Jia Liu
https://arxiv.org/abs/2508.13451 https://

Benchmarking spike source localization algorithms in high density probes
Estimating neuron location from extracellular recordings is essential for developing advanced brain-machine interfaces. Accurate neuron localization improves spike sorting, which involves detecting action potentials and assigning them to individual neurons. It also helps monitor probe drift, which affects long-term probe reliability. Although several localization algorithms are currently in use, the field is nascent and arguments for using one algorithm over another are largely theoretical or b…

cintestinalis: Tadpole larva brain (C. intestinalis)
Entire connectivity matrix for the complete brain of a larva of Ciona intestinalis. Each directed edge represents a synaptic connection from pre-synaptic cell i to post-synaptic cell j (may not be a neuron). Edge weights represent the cumulative depth of presynaptic contacts in µm.
This network has 205 nodes and 2903 edges.
Tags: Biological, Connectome, Weighted

Context dependent adaptation in a neural computation
Charles J. Edelson, Sima Setayeshgar, William Bialek, Rob R. de Ruyter van Steveninck
https://arxiv.org/abs/2509.01760 https…

Context dependent adaptation in a neural computation
Brains adapt to the statistical structure of their input. In the visual system, local light intensities change rapidly, the variance of the intensity changes more slowly, and the dynamic range of contrast itself changes more slowly still. We use a motion-sensitive neuron in the fly visual system to probe this hierarchy of adaptation phenomena, delivering naturalistic stimuli that have been simplified to have a clear separation of time scales. We show that the neural response to visual motion de…

cintestinalis: Tadpole larva brain (C. intestinalis)
Entire connectivity matrix for the complete brain of a larva of Ciona intestinalis. Each directed edge represents a synaptic connection from pre-synaptic cell i to post-synaptic cell j (may not be a neuron). Edge weights represent the cumulative depth of presynaptic contacts in µm.
This network has 205 nodes and 2903 edges.
Tags: Biological, Connectome, Weighted

Computational Advances in Taste Perception: From Ion Channels to Neural Coding
Vladimir A. Lazovsky, Sergey V. Stasenko, Victor B. Kazantsev
https://arxiv.org/abs/2510.00010 htt…

Computational Advances in Taste Perception: From Ion Channels to Neural Coding
Recent advances in computational neuroscience demand models that balance biophysical realism with scalability. We present a hybrid neuron model combining the biophysical fidelity of Hodgkin-Huxley (HH) dynamics for taste receptor cells with the computational efficiency of Izhikevich spiking neurons for large-network simulations. Our framework incorporates biomorphic taste cell models, featuring modality-specific receptor dynamics (T1R/T2R, ENaC, PKD) and Goldman-Hodgkin-Katz (GHK)-driven ion cu…

cintestinalis: Tadpole larva brain (C. intestinalis)
Entire connectivity matrix for the complete brain of a larva of Ciona intestinalis. Each directed edge represents a synaptic connection from pre-synaptic cell i to post-synaptic cell j (may not be a neuron). Edge weights represent the cumulative depth of presynaptic contacts in µm.
This network has 205 nodes and 2903 edges.
Tags: Biological, Connectome, Weighted

fly_larva: Drosophila larva brain (2023)
A complete synaptic map of the brain connectome of the larva of the fruit fly Drosophila melanogaster. Nodes are neurons, and edges are synaptic connections, traced individually from brain image sections using three-dimensional electron microscopy–based reconstruction. Node metadata include the neuron hempisphere, hemispherical homologue, cell type, annotations, and inferred cluster. Edge metadata include the type of interaction (`'aa'`,…