会员服务
Do LLMs Signal When They're Right? Evidence from Neuron Agreement
Arxiv
0+阅读 · 10月30日
Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics
Arxiv
0+阅读 · 10月30日
Modeling Neural Activity with Conditionally Linear Dynamical Systems
Modeling Neural Activity with Conditionally Linear Dynamical Systems
Arxiv
0+阅读 · 10月30日
Dissecting Role Cognition in Medical LLMs via Neuronal Ablation
Dissecting Role Cognition in Medical LLMs via Neuronal Ablation
Arxiv
0+阅读 · 10月28日
Improving Model Fusion by Training-time Neuron Alignment with Fixed Neuron Anchors
Arxiv
0+阅读 · 10月27日
One-Timestep is Enough: Achieving High-performance ANN-to-SNN Conversion via Scale-and-Fire Neurons
Arxiv
0+阅读 · 10月27日
Engram Memory Encoding and Retrieval: A Neurocomputational Perspective
Arxiv
0+阅读 · 10月24日
VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
Arxiv
0+阅读 · 10月24日
Leverage Unlearning to Sanitize LLMs
Arxiv
0+阅读 · 10月24日
Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
Arxiv
0+阅读 · 10月24日
Spark Transformer: Reactivating Sparsity in FFN and Attention
Arxiv
0+阅读 · 10月23日
Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
Arxiv
0+阅读 · 10月23日
Decomposing stimulus-specific sensory neural information via diffusion models
Arxiv
0+阅读 · 10月22日
Automated Morphological Analysis of Neurons in Fluorescence Microscopy Using YOLOv8
Arxiv
0+阅读 · 10月22日
Viability of perturbative expansion for quantum field theories on neurons
Viability of perturbative expansion for quantum field theories on neurons
Arxiv
0+阅读 · 10月21日
参考链接
微信扫码咨询专知VIP会员
Top