相关论文: Neurons in Large Language Models: Dead, N-gram, Po…

A pressing scientific challenge is to understand how brains work. Of particular interest is the neocortex,the part of the brain that is especially large in humans, capable of handling a wide variety of tasks including visual, auditory,…

Transfer learning from pre-trained neural language models towards downstream tasks has been a predominant theme in NLP recently. Several researchers have shown that deep NLP models learn non-trivial amount of linguistic knowledge, captured…

The linear independence of neurons plays a significant role in theoretical analysis of neural networks. Specifically, given neurons $H_1, ..., H_n: \bR^N \times \bR^d \to \bR$, we are interested in the following question: when are…

Generative large language models (LLMs) excel in natural language processing tasks, yet their inner workings remain underexplored beyond token-level predictions. This study investigates the degree to which these models decide the content of…

Graphs are a powerful data structure for representing relational data and are widely used to describe complex real-world systems. Probabilistic Graphical Models (PGMs) and Graph Neural Networks (GNNs) can both leverage graph-structured…

Seminal works on graph neural networks have primarily targeted semi-supervised node classification problems with few observed labels and high-dimensional signals. With the development of graph networks, this setup has become a de facto…

Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters associated with the…

The increasing size of large neural network models, specifically language models and foundational image models, poses deployment challenges, prompting efforts to reduce memory requirements and enhance computational efficiency. These efforts…

The large number of parameters in Pretrained Language Models enhance their performance, but also make them resource-intensive, making it challenging to deploy them on commodity hardware like a single GPU. Due to the memory and power…

Pervasive polysemanticity in large language models (LLMs) undermines discrete neuron-concept attribution, posing a significant challenge for model interpretation and control. We systematically analyze both encoder and decoder based LLMs…

Deep neural networks (DNNs) have made significant strides in tackling challenging tasks in wireless systems, especially when an accurate wireless model is not available. However, when available data is limited, traditional DNNs often yield…

Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, we introduce a simple, lightweight, and broadly applicable method with a focus on…

Visual world studies show that upon hearing a word in a target-absent visual context containing related and unrelated items, toddlers and adults briefly direct their gaze towards phonologically related items, before shifting towards…

It is becoming increasingly appreciated that the signal transduction systems used by eukaryotic cells to achieve a variety of essential responses represent highly complex networks rather than simple linear pathways. While significant effort…

Large Language Models (LLMs) demonstrate impressive performance across natural language tasks but incur substantial computational and storage costs due to their scale. Post-training structured pruning offers an efficient solution. However,…

Neuroscientists fit morphologically and biophysically detailed neuron simulations to physiological data, often using evolutionary algorithms. However, such gradient-free approaches are computationally expensive, making convergence slow when…

Though traditional algorithms could be embedded into neural architectures with the proposed principle of \cite{xiao2017hungarian}, the variables that only occur in the condition of branch could not be updated as a special case. To tackle…

While feed-forward neurons in pre-trained language models (PLMs) can encode knowledge, past research targeted a small subset of neurons that heavily influence outputs. This leaves the broader role of neuron activations unclear, limiting…

The remarkable success of large language models (LLMs) stems from their ability to consolidate vast amounts of knowledge into the memory during pre-training and to retrieve it from the memory during inference, enabling advanced capabilities…

Some neurons in deep networks specialize in recognizing highly specific perceptual, structural, or semantic features of inputs. In computer vision, techniques exist for identifying neurons that respond to individual concept categories like…