Neurons

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 175% on the four weeks before. 0.3% of all new papers.

Jul 6Week of Sep 21

Latest papers 134

All topics

Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
Apr 24, 2026Oussama Bouanani, Jim Berend, Wojciech Samek +2Contrastive Learning Neurons
Fraunhofer Heinrich Hertz Institute, Berlin, Germany · Technische Universität Berlin, Berlin, Germany · BIFOLD – Berlin Institute for the Foundations of Learning and Data, Berlin, Germany +1
Response time of lateral predictive coding and benefits of modular structures
Apr 22, 2026Guanghui Cai, Zhen-Ye Huang, Weikang Wang +1Predictive Coding Latent Prediction
Institute of Theoretical Physics, Chinese Academy of Sciences, ZhongGuanCun East Road 55, Beijing 100190, China · Westlake Institute for Advanced Study, Hangzhou 310024, China · Center for Interdisciplinary Studies and Department of Physics, School of Science, Westlake University, Hangzhou 310030, China +2
Where Fake Citations Are Made: Tracing Field-Level Hallucination to Specific Neurons in LLMs
Apr 20, 2026Yuefei Chen, Yihao Quan, Xiaodong Lin +1Citation Hallucination Visual Hallucinations
Rutgers University
From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models
Apr 20, 2026Qidong Wang, Junjie Hu, Ming JiangRecent Vision-Language Models Neurons
Tongji University · University of Wisconsin-Madison
ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data
Apr 19, 2026Gareth Seneque, Lap-Hang Ho, Nafise Erfanian Saeedi +2Atlas Discriminative Congruence Transform
Australian Broadcasting Corporation
Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering
Apr 19, 2026Li Zheng, Xin Zhang, Shuyi He +5Rhetoric Neurons
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China · Ant International · School of Computing Technologies, RMIT University, Australia
Equivalence of approximation by networks of single- and multi-spike neurons
Mar 13, 2026Dominik Dold, Philipp Christian PetersenSpiking Neural Networks Time-To-First-Spike
Teaching signal synchronization in deep neural networks with prospective neurons
Nov 18, 2025Nicolas Zucchet, Qianqian Feng, Axel Laborieux +3Synaptic Plasticity Neurons
Computer Science Department, ETH Zürich · Gatsby Computational Neuroscience Unit, University College London · Friedrich Miescher Institute for Biomedical Research +3
Redundancy Maximization as a Principle of Associative Memory Learning in Hopfield Networks
Nov 4, 2025Mark Blümel, Andreas C. Schneider, Valentin Neuhaus +5Hopfield Networks Dense Associative Memory
Complex Systems Theory, Max Planck Institute for Dynamics and Self-Organization, Göttingen, Germany · Faculty of Physics, Institute for the Dynamics of Complex Systems, University of Göttingen · Göttingen Campus Institute for Dynamics of Biological Networks, University of Göttingen, Göttingen, Germany +1
Nonlinear Dynamics In Optimization Landscape of Shallow Neural Networks with Tunable Leaky ReLU
Oct 29, 2025Jingzhou LiuRectified Linear Unit Neurons
A memory-based active inference model of DishBrain-like adaptive behaviour
Aug 9, 2025Aswin Paul, Moein Khajehnejad, Forough Habibollahi +2Brain-Inspired Synergistic Framework Inference-Time Steering
Turner Institute for Brain and Mental Health, School of Psychological Sciences, Monash University, Clayton 3800, Australia · VERSES, Los Angeles, California, USA · Cortical Labs Pty Ltd, Melbourne 3056, Australia +1
On the Interaction of Compressibility and Adversarial Robustness
Jul 23, 2025Melih Barsbey, Antônio H. Ribeiro, Umut Şimşekli +1Compressed Model Data Compression Methods
Department of Computing, Imperial College London, UK · Department of Information Technology, Uppsala University, Sweden · INRIA, CNRS, Département d’Informatique de l’Ecole Normale Supérieure / PSL, France
Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning
Feb 2, 2025Zeyu Jiang, Hai Huang, Xingquan ZuoInterpretability Neurons
School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
Perforated Backpropagation: A Neuroscience Inspired Extension to Artificial Neural Networks
Jan 29, 2025Rorry Brenner, Laurent IttiNeurons Backpropagation
Perforated AI Inc. · Computer Science and Neuroscience, University of Southern California

Apr 24, 2026, cs.CVJ/K move · Enter open · S save

Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples

Oussama Bouanani, Jim Berend, Wojciech Samek, Sebastian Lapuschkin+1

Fraunhofer Heinrich Hertz Institute, Berlin, Germany · Technische Universität Berlin, Berlin, Germany · BIFOLD – Berlin Institute for the Foundations of Learning and Data, Berlin, Germany+1

Contrastive Learning Neurons Interpretability Projection Encoders

Open paper AskPDF arXiv

Neuron labeling assigns textual descriptions to internal units of deep networks. Existing approaches typically rely on highly activating examples, often yielding broad or misleading labels by focusing on dominant but incidental visual factors. Prior work such as FALCON introduced contrastive examples -- inputs that are semantically similar to activating examples but elicit low activations -- to sharpen explanations, but it primarily addresses subspace-level interpretability rather than scalable neuron-level labeling. We revisit contrastive explanations for neuron-level labeling in two stages: (1) candidate label generation with vision language models (VLMs) and (2) label assignment with CLIP-like encoders. First, we show that providing contrastive image sets to VLMs yields candidate labels that are more specific and more faithful. Second, we introduce Contrastive Semantic Projection (CSP), an extension of SemanticLens that incorporates contrastive examples directly into its CLIP-based scoring and selection pipeline. Across extensive experiments and a case study on melanoma detection, contrastive labeling improves both faithfulness and semantic granularity over state-of-the-art baselines. Our results demonstrate that contrastive examples are a simple yet powerful and currently underutilized component of neuron labeling and analysis pipelines.

Momentum

Related topics

Latest papers 134