相关论文: GLUScope: A Tool for Analyzing GLU Neurons in Tran…

Spiking Neural Networks (SNNs) have been studied over decades to incorporate their biological plausibility and leverage their promising energy efficiency. Throughout existing SNNs, the leaky integrate-and-fire (LIF) model is commonly…

We present LINSPECTOR WEB, an open source multilingual inspector to analyze word representations. Our system provides researchers working in low-resource settings with an easily accessible web based probing tool to gain quick insights into…

The current Large Language Models (LLMs) face significant challenges in improving their performance on low-resource languages and urgently need data-efficient methods without costly fine-tuning. From the perspective of language-bridge, we…

The goal of this paper is to report certain scientific discoveries about a Seq2Seq model. It is known that analyzing the behavior of RNN-based models at the neuron level is considered a more challenging task than analyzing a DNN or CNN…

We present a methodology that explores how sentence structure is reflected in neural representations of machine translation systems. We demonstrate our model-agnostic approach with the Transformer English-German translation model. We…

Reliable evaluation benchmarks designed for replicability and comprehensiveness have driven progress in machine learning. Due to the lack of a multilingual benchmark, however, vision-and-language research has mostly focused on English…

Hallucination detection in Large Language Models (LLMs) is crucial for ensuring their reliability. This work presents our participation in the CLEF ELOQUENT HalluciGen shared task, where the goal is to develop evaluators for both generating…

As powerful pre-trained vision-language models (VLMs) like CLIP gain prominence, numerous studies have attempted to combine VLMs for downstream tasks. Among these, prompt learning has been validated as an effective method for adapting to…

This chapter illustrates how suitable neuro-symbolic models for language understanding can enable domain generalizability and robustness in downstream tasks. Different methods for integrating neural language models and knowledge graphs are…

Recent work on non-autoregressive neural machine translation (NAT) aims at improving the efficiency by parallel decoding without sacrificing the quality. However, existing NAT methods are either inferior to Transformer or require multiple…

Several text classification tasks such as sentiment analysis, news categorization, multi-label classification and opinion classification are challenging problems even for modern deep learning networks. Recently, Capsule Networks (CapsNets)…

Graph Convolutional Networks (GCNs) have proven to be highly effective for skeleton-based action recognition, primarily due to their ability to leverage graph topology for feature aggregation, a key factor in extracting meaningful…

Mechanistic interpretability research requires reliable tools for analyzing transformer internals across diverse architectures. Current approaches face a fundamental tradeoff: custom implementations like TransformerLens ensure consistent…

Extracting stimulus features from neuronal ensembles is of great interest to the development of neuroprosthetics that project sensory information directly to the brain via electrical stimulation. Machine learning strategies that optimize…

Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood. Existing interpretability work on VLMs uses Sparse Autoencoders (SAEs), which decompose…

A graph neural network (GNN) for image understanding based on multiple cues is proposed in this paper. Compared to traditional feature and decision fusion approaches that neglect the fact that features can interact and exchange information,…

Generative adversarial networks (GANs) are increasingly attracting attention in the computer vision, natural language processing, speech synthesis and similar domains. However, evaluating the performance of GANs is still an open and…

Deep learning tools are being used extensively in high energy physics and are becoming central in the reconstruction of neutrino interactions in particle detectors. In this work, we report on the performance of a graph neural network in…

Large language models (LLMs) such as GPT and Gemini have demonstrated remarkable capabilities in contextual understanding and reasoning. The strong performance of LLMs has sparked growing interest in leveraging them to automate tasks…

Inspired by cognitive neuroscience studies, we introduce a novel `decoding probing' method that uses minimal pairs benchmark (BLiMP) to probe internal linguistic characteristics in neural language models layer by layer. By treating the…