1
谷歌首绘果蝇全脑图谱，超 16.6 万神经元被开发者拉去训练《毁灭战士》
IT之家 9 月 9 日消息，科技媒体 Tom's Hardware 昨日（9 月 8 日）发布博文，报道称谷歌首次绘制成年雄果蝇完整神经图谱后， 开发者 Alex Wormuth 使用完整 MaleCNS v1.0 连接组训练《毁灭战士》。 MaleCNS v1.0 是成年雄性黑腹果蝇中枢神经系统…
2
Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron
发现单个神经元就能像旋钮一样控制LLM的投资偏见，精准干预AI决策倾向。
arXiv:2608.22852v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows…
3
Eon用LIF“上传”果蝇脑，中国团队直接上精细神经元和跨身体平台
将真实场景重建为持续更新、可计算的4D数字世界。
4
SafeNexus: Discovering and Steering Modality-Universal Safety Neurons in MLLMs
破解多模态大模型安全短板，定位并操控通用安全神经元，为AI对齐提供新思路
arXiv:2607.28969v1 Announce Type: new Abstract: Although Large Language Models (LLMs) have demonstrated promising safety performance, extending them t…
5
Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs
阿拉伯语方言能否像语言一样被定向操控？稀疏神经元与分布式方向的机制揭秘，为大模型方言控制打开新思路。
arXiv:2607.03936v1 Announce Type: new Abstract: A key challenge in Arabic NLP is the scarcity of dialectal data relative to Modern Standard Arabic (MS…
6
Faithfulness to Refusal: A Causal Audit of Neuron Selectors
用因果审计拆解神经元选择器，探究模型拒绝行为是否忠实可靠，值得深读。
arXiv:2607.05355v1 Announce Type: cross Abstract: Attribution scores increasingly identify which neuron rows of a language model matter for applicatio…
7
Neuron-Aware Active Few-Shot Learning for LLMs
LLM领域新突破：神经元感知主动少样本学习，精准挑选标注样本，大幅节省人力成本。
arXiv:2607.02423v1 Announce Type: cross Abstract: Active Few-Shot Learning (AFSL) adapts LLMs to specialized domains by identifying the most valuable …
8
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
无需人工标注，通过神经元激活模式筛选数据，实现LLM高效自蒸馏训练。
arXiv:2607.02460v1 Announce Type: cross Abstract: Post-training large language models (LLMs) without real-world interaction feedback or human-labeled …
9
全球首次：我国科学家实现单神经元三模态完整解析
全球首次实现同一神经元功能、结构与基因的同步解析，打破数据孤岛，为神经科学和AI交叉研究开辟新路径。
IT之家 6 月 19 日消息，据央视报道，中国科学院脑科学与智能技术卓越创新中心王凯研究团队与徐圣进研究团队联合在国际顶级学术期刊《细胞》上发表了一项重磅研究成果。 研究团队自主研发出基于成像的多模态解析平台“IMC”（Imaging-based Multimodal Characterizati…
10
How the brain builds sentences, neuron by neuron
从单个神经元实时记录看大脑如何逐字构建句子，颠覆语言认知。
Nature, Published online: 17 June 2026; doi:10.1038/d41586-026-01922-w Neural maps reveal the specialized cells that produce speech.
11
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs
多模态大语言模型在配对时表现准确、拆分时出错，研究通过解耦编辑特定模态神经元来修复这一现象。
arXiv:2606.17057v1 Announce Type: cross Abstract: Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal …
12
Neuron Level Analysis of Large Language Model in Legal Domain Reasoning
从神经元层面剖析大模型在法律推理中的内部机制，揭示模型如何理解和应用法律规则
arXiv:2606.15884v1 Announce Type: new Abstract: We presented a neuron-level analysis of legal-domain reasoning in LLMs, comparing it with other applie…
13
NeST: Neuron Selective Tuning for LLM Safety
大模型安全新方案：通过神经元选择性调优NeST精准提升LLM安全性，不牺牲性能。
arXiv:2602.16835v2 Announce Type: replace-cross Abstract: Safety alignment is essential for the responsible deployment of Large Language Models (LLMs)…
14
Can Editing 1 Neuron Fix Repetition Loops in LLMs?
编辑单个神经元，就能修复大模型在长枚举任务中的重复循环崩溃？这项研究揭示了 Gemma 4 模型的深层问题与解法。
arXiv:2606.13705v1 Announce Type: cross Abstract: Yes. Can it cure doom loops? Probably not. The Gemma 4 instruction-tuned models share a reproducible…
15
Neural FOXP2 -- Language Specific Neuron Steering for Targeted Language Improvement in LLMs
从基因隐喻到模型微调，揭秘如何通过语言特定神经元定向提升大模型多语言性能
arXiv:2602.00945v2 Announce Type: replace-cross Abstract: LLMs are multilingual by training, yet their lingua franca is often English, reflecting Engl…
16
Neuron-based Personality Trait Induction in Large Language Models
ICLR 2025论文揭示如何通过神经元干预为LLM注入特定人格特质，打开模型个性化新维度。
arXiv:2410.12327v2 Announce Type: replace Abstract: Large language models (LLMs) have become increasingly proficient at simulating various personality…
17
TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts
MoE大模型专家剪枝新方法，梯形剪枝保留路由拓扑，大幅压缩静态参数占用。
arXiv:2606.09885v1 Announce Type: new Abstract: Mixture-of-Experts large language models (LLMs) scale efficiently through sparse activation, yet their…
18
Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts
用少量提示即可精准定位大模型中的关键神经元，揭示AI“大脑”的运作秘密。
arXiv:2605.24846v1 Announce Type: cross Abstract: Large language models (LLMs) display strong comprehensive abilities, yet the internal mechanisms tha…
19
Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
通过引入“自发性”机制，显著提升大语言模型激活稀疏性的鲁棒性，为高效推理提供新思路。
arXiv:2512.12744v4 Announce Type: replace Abstract: Activation sparsity offers a compelling route to accelerate large language model (LLM) inference b…