GENA-LM: a family of open-source foundational DNA language models for long sequences

V Fishman, Y Kuratov, A Shmelev… - Nucleic Acids …, 2025 - academic.oup.com
Recent advancements in genomics, propelled by artificial intelligence, have unlocked
unprecedented capabilities in interpreting genomic sequences, mitigating the need for …

Infinipot: Infinite context processing on memory-constrained llms

M Kim, K Shim, J Choi, S Chang - arXiv preprint arXiv:2410.01518, 2024 - arxiv.org
Handling long input contexts remains a significant challenge for Large Language Models
(LLMs), particularly in resource-constrained environments such as mobile devices. Our work …

BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack

Y Kuratov, A Bulatov, P Anokhin, I Rodkin… - arXiv preprint arXiv …, 2024 - arxiv.org
In recent years, the input context sizes of large language models (LLMs) have increased
dramatically. However, existing evaluation methods have not kept pace, failing to …

Length Generalization with Recursive Neural Networks and Beyond

JR Chowdhury - 2024 - search.proquest.com
Abstract We investigate Recursive Neural Networks (RvNNs) for language processing tasks.
Roughly, from a generalized perspective, RvNNs repeatedly apply some neural function on …

Platform Economy in Emerging-Market China: State-Corporate Relations, Market Reorganization, and Worker Welfare

Q Song - 2024 - search.proquest.com
The platform economy, an economic system that relies on digital platforms to mediate the
exchange of goods, services, and information—such as Uber, Amazon, and Upwork—has …

[PDF][PDF] What Do Platform Workers Think?: Analysis of Truck Drivers' Perspectives on Digital Platforms Using GPT-4

Q Song, K Jia - osf.io
This study examines platform workers' experiences and perspectives about digital platforms
in the Chinese freight transportation industry based on a large dataset of self-employed truck …

New Frontiers in Associative Memories

J Kempe, D Krotov, H Kuehne, D Lee… - ICLR 2025 Workshop … - openreview.net
This workshop will discuss the latest multidisciplinary developments in Associative Memory.
A number of leading researchers in this topic from around the world have already agreed to …

Recurrent memory augmentation of GENA-LM improves performance on long DNA sequence tasks

Y Kuratov, A Shmelev, V Fishman, O Kardymon… - ICLR 2024 Workshop on … - openreview.net
Utilizing DNA language models based on the transformer architecture represents a
significant advancement in the field of computational genomics. However, these models face …