Related papers: Automated Protein Motif Localization using Concept…

Proteins perform essential biological functions, and accurate classification of their sequences is critical for understanding structure-function relationships, enzyme mechanisms, and molecular interactions. This study presents a deep…

Protein representation learning has primarily benefited from the remarkable development of language models (LMs). Accordingly, pre-trained protein models also suffer from a problem in LMs: a lack of factual knowledge. The recent solution…

Protein Language Models (PLMs), pre-trained on extensive evolutionary data from natural proteins, have emerged as indispensable tools for protein design. While powerful, PLMs often struggle to produce proteins with precisely specified…

In this work, we examine how targeted perturbations in the activation space of Language Models (LMs) can encode complex reasoning patterns. We inject steering vectors, derived from LM activations, into LMs during inference time and study…

Protein language models (PLMs) have revolutionised computational biology through their ability to generate powerful sequence representations for diverse prediction tasks. However, their black-box nature limits biological interpretation and…

One of the long-standing challenges in lexical semantics consists in learning representations of words which reflect their semantic properties. The remarkable success of word embeddings for this purpose suggests that high-quality…

The problem of motif detection can be formulated as the construction of a discriminant function to separate sequences of a specific pattern from background. In computational biology, motif detection is used to predict DNA binding sites of a…

Neural language models have become powerful tools for learning complex representations of entities in natural language processing tasks. However, their interpretability remains a significant challenge, particularly in domains like…

Genes carry the instructions for making proteins that are found in a cell as a specific sequence of nucleotides that are found in DNA molecules. But, the regions of these genes that code for proteins may occupy only a small region of the…

Unlocking the next generation of biotechnology and therapeutic innovation demands overcoming the inherent complexity and resource-intensity of conventional protein engineering methods. Recent GenAI-powered computational techniques often…

While protein language models (PLMs) are one of the most promising avenues of research for future de novo protein design, the way in which they transform sequences to hidden representations, as well as the information encoded in such…

Concept Activation Vectors (CAVs) offer insights into neural network decision-making by linking human friendly concepts to the model's internal feature extraction process. However, when a new set of CAVs is discovered, they must still be…

Multimodal Emotion Recognition refers to the classification of input video sequences into emotion labels based on multiple input modalities (usually video, audio and text). In recent years, Deep Neural networks have shown remarkable…

Concept Activation Vectors (CAVs) are a tool from explainable AI, offering a promising approach for understanding how human-understandable concepts are encoded in a model's latent spaces. They are computed from hidden-layer activations of…

Pre-trained vision-language models (VLMs) have shown impressive performance on various downstream tasks by utilizing knowledge learned from large data. In general, the performance of VLMs on target tasks can be further improved by prompt…

Protein sequence design, determined by amino acid sequences, are essential to protein engineering problems in drug discovery. Prior approaches have resorted to evolutionary strategies or Monte-Carlo methods for protein design, but often…

Vision-language models (VLMs) have made significant progress in image classification by training with large-scale paired image-text data. Their performances largely depend on the prompt quality. While recent methods show that visual…

The design of protein sequences with desired functionalities is a fundamental task in protein engineering. Deep generative methods, such as autoregressive models and diffusion models, have greatly accelerated the discovery of novel protein…

We consider the generic problem of detecting low-level structures in images, which includes segmenting the manipulated parts, identifying out-of-focus pixels, separating shadow regions, and detecting concealed objects. Whereas each such…

To interpret deep learning models, one mainstream is to explore the learned concepts by networks. Testing with Concept Activation Vector (TCAV) presents a powerful tool to quantify the contribution of query concepts (represented by…