相关论文: Wisteria: A Unified Multi-Scale Feature Learning F…

A fundamental property of DNA is that the reverse complement (RC) of a sequence often carries identical biological meaning. However, state-of-the-art DNA language models frequently fail to capture this symmetry, producing inconsistent…

Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations from scratch -- computationally expensive and yielding verbose code. We propose Delta-Code…

Large Language Models (LLMs) have significantly advanced artificial intelligence, excelling in numerous tasks. Although the functionality of a model is inherently tied to its parameters, a systematic method for exploring the connections…

Multilingual transfer ability, which reflects how well models fine-tuned on one source language can be applied to other languages, has been well studied in multilingual pre-trained models. However, the existence of such capability transfer…

Multi-view datasets offer diverse forms of data that can enhance prediction models by providing complementary information. However, the use of multi-view data leads to an increase in high-dimensional data, which poses significant challenges…

Despite a plethora of anomaly detection models developed over the years, their ability to generalize to unseen anomalies remains an issue, particularly in critical systems. This paper aims to address this challenge by introducing Swift…

Research on long non-coding RNAs (lncRNAs) has garnered significant attention due to their critical roles in gene regulation and disease mechanisms. However, the complexity and diversity of lncRNA sequences, along with the limited knowledge…

Existing methods for vision-and-language learning typically require designing task-specific architectures and objectives for each task. For example, a multi-label answer classifier for visual question answering, a region scorer for…

Modern language models scale depth by stacking layers, each holding its own state - a per-layer KV cache in transformers, a per-layer matrix in Mamba, Gated DeltaNet (GDN), RWKV, and xLSTM. Biological systems lean heavily on recurrence…

The rapid advancement of DNA sequencing has produced vast genomic datasets, yet interpreting and engineering genomic function remain fundamental challenges. Recent large language models have opened new avenues for genomic analysis, but…

We propose a novel methodology to address dialog learning in the context of goal-oriented conversational systems. The key idea is to quantize the dialog space into clusters and create a language model across the clusters, thus allowing for…

Protein is linked to almost every life process. Therefore, analyzing the biological structure and property of protein sequences is critical to the exploration of life, as well as disease detection and drug discovery. Traditional protein…

Projecting visual features into word embedding space has become a significant fusion strategy adopted by Multimodal Large Language Models (MLLMs). However, its internal mechanisms have yet to be explored. Inspired by multilingual research,…

The pre-dominant approach to language modeling to date is based on recurrent neural networks. Their success on this task is often linked to their ability to capture unbounded context. In this paper we develop a finite context approach…

While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which addresses both families of tasks simultaneously. We…

Generative machine learning models offer a powerful framework for therapeutic design by efficiently exploring large spaces of biological sequences enriched for desirable properties. Unlike supervised learning methods, which require both…

Vision-language large models are moving toward the unification of visual understanding and visual generation tasks. However, whether generation can enhance understanding is still under-explored on large data scale. In this work, we analysis…

Foundation models have received much attention due to their effectiveness across a broad range of downstream applications. Though there is a big convergence in terms of architecture, most pretrained models are typically still developed for…

Recent advances in language models opened new opportunities to address complex schema matching tasks. Schema matching approaches have been proposed that demonstrate the usefulness of language models, but they have also uncovered important…

We propose WirelessJEPA, a novel wireless foundation model (WFM) that uses the Joint Embedding Predictive Architecture (JEPA). WirelessJEPA learns general-purpose representations directly from real-world multi-antenna IQ data by predicting…