Related papers: GLUScope: A Tool for Analyzing GLU Neurons in Tran…

In today's world of big data, computational analysis has become a key driver of biomedical research. Recent exponential growth in the volume of available omics data has reshaped the landscape of contemporary biology, creating demand for a…

Given the fast development of analysis techniques for NLP and speech processing systems, few systematic studies have been conducted to compare the strengths and weaknesses of each method. As a step in this direction we study the case of…

Pretrained Language Models (PLMs) benefit from external knowledge stored in graph structures for various downstream tasks. However, bridging the modality gap between graph structures and text remains a significant challenge. Traditional…

This paper introduces DogSurf - a newapproach of using quadruped robots to help visually impaired people navigate in real world. The presented method allows the quadruped robot to detect slippery surfaces, and to use audio and haptic…

The ability to compositionally map language to referents, relations, and actions is an essential component of language understanding. The recent gSCAN dataset (Ruis et al. 2020, NeurIPS) is an inspiring attempt to assess the capacity of…

Writing is a universal cultural technology that reuses vision for symbolic communication. Humans display striking resilience: we readily recognize words even when characters are fragmented, fused, or partially occluded. This paper…

Practical needs of developing task-oriented dialogue assistants require the ability to understand many languages. Novel benchmarks for multilingual natural language understanding (NLU) include monolingual sentences in several languages,…

Understanding the role of (stochastic) gradient descent (SGD) in the training and generalisation of deep neural networks (DNNs) with ReLU activation has been the object study in the recent past. In this paper, we make use of deep gated…

Much of today's machine learning research involves interpreting, modifying or visualizing models after they are trained. I present Penzai, a neural network library designed to simplify model manipulation by representing models as simple…

Recent work has shown that imperceptible perturbations can be applied to craft unlearnable examples (ULEs), i.e. images whose content cannot be used to improve a classifier during training. In this paper, we reveal the road that researchers…

We present minicons, an open source library that provides a standard API for researchers interested in conducting behavioral and representational analyses of transformer-based language models (LMs). Specifically, minicons enables…

The use of large language models (LLMs) as feature enhancers to optimize node representations, which are then used as inputs for graph neural networks (GNNs), has shown significant potential in graph representation learning. However, the…

Continual locomotion learning faces four challenges: incomprehensibility, sample inefficiency, lack of knowledge exploitation, and catastrophic forgetting. Thus, this work introduces Growable Online Locomotion Learning Under Multicondition…

Motivation: Cell-biological processes are regulated through a complex network of interactions between genes and their products. The processes, their activating conditions, and the associated transcriptional responses are often unknown.…

Transformer is a state-of-the-art model in the field of natural language processing (NLP). Current NLP models primarily increase the number of transformers to improve processing performance. However, this technique requires a lot of…

Recently, deep neural networks (DNNs) have achieved great success in semantically challenging NLP tasks, yet it remains unclear whether DNN models can capture compositional meanings, those aspects of meaning that have been long studied in…

Gated Recurrent Unit (GRU) is a recently-developed variation of the long short-term memory (LSTM) unit, both of which are types of recurrent neural network (RNN). Through empirical evidence, both models have been proven to be effective in a…

Psycholinguistic research suggests that humans may build a representation of linguistic input that is 'good-enough' for the task at hand. This study examines what architectural features make language models learn human-like good-enough…

Natural language generation (NLG) plays a critical role in spoken dialogue systems. This paper presents a new approach to NLG by using recurrent neural networks (RNN), in which a gating mechanism is applied before RNN computation. This…

Training vision-language models on cognitively-plausible amounts of data requires rethinking how models integrate multimodal information. Within the constraints of the Vision track for the BabyLM Challenge 2025, we propose a lightweight…