Related papers: SALSA: Semantically-Aware Latent Space Autoencoder

Chemical autoencoders are attractive models as they combine chemical space navigation with possibilities for de-novo molecule generation in areas of interest. This enables them to produce focused chemical libraries around a single lead…

Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…

Sign language recognition (SLR) has long been plagued by insufficient model representation capabilities. Although current pre-training approaches have alleviated this dilemma to some extent and yielded promising performance by employing…

In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional…

Autoencoder can give rise to an appropriate latent representation of the input data, however, the representation which is solely based on the intrinsic property of the input data, is usually inferior to express some semantic information. A…

The pixel-wise dense prediction tasks based on weakly supervisions currently use Class Attention Maps (CAM) to generate pseudo masks as ground-truth. However, the existing methods typically depend on the painstaking training modules, which…

Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only…

Deep learning methodology contributes a lot to the development of hyperspectral image (HSI) analysis community. However, it also makes HSI analysis systems vulnerable to adversarial attacks. To this end, we propose a masked spatial-spectral…

Accurately predicting drug-target binding affinity (DTA) in silico is a key task in drug discovery. Most of the conventional DTA prediction methods are simulation-based, which rely heavily on domain knowledge or the assumption of having the…

Despite their impressive generalization capabilities, instruction-tuned Large Language Models often underperform on text classification benchmarks. We introduce SALSA, a coherent pipeline that combines structured prompting, class-to-token…

Deep generative models are increasingly becoming integral parts of the in silico molecule design pipeline and have dual goals of learning the chemical and structural features that render candidate molecules viable while also being flexible…

An autoencoder is a neural network which data projects to and from a lower dimensional latent space, where this data is easier to understand and model. The autoencoder consists of two sub-networks, the encoder and the decoder, which carry…

Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…

Drug-target binding affinity prediction plays an important role in the early stages of drug discovery, which can infer the strength of interactions between new drugs and new targets. However, the performance of previous computational models…

Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-trivial because the…

Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…

Variational autoencoders (VAEs) defined over SMILES string and graph-based representations of molecules promise to improve the optimization of molecular properties, thereby revolutionizing the pharmaceuticals and materials industries.…

Autoencoders have been used for finding interpretable and disentangled features underlying neural network representations in both image and text domains. While the efficacy and pitfalls of such methods are well-studied in vision, there is a…

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end…

In this paper, we proposed an integrated model of semantic-aware and contrast-aware saliency combining both bottom-up and top-down cues for effective saliency estimation and eye fixation prediction. The proposed model processes visual…