skip to main content

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Thursday, February 13 until 2:00 AM ET on Friday, February 14 due to maintenance. We apologize for the inconvenience.


Search for: All records

Creators/Authors contains: "Yuan, Jianbo"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Diffusion models excel at generating photo-realistic images but come with significant computational costs in both training and sampling. While various techniques address these computational challenges, a less-explored issue is designing an efficient and adaptable network backbone for iterative refinement. Current options like U-Net and Vision Transformer often rely on resource-intensive deep networks and lack the flexibility needed for generating images at variable resolutions or with a smaller network than used in training. This study introduces LEGO bricks, which seamlessly integrate Local-feature Enrichment and Global-content Orchestration. These bricks can be stacked to create a test-time reconfigurable diffusion backbone, allowing selective skipping of bricks to reduce sampling costs and generate higher-resolution images than the training data. LEGO bricks enrich local regions with an MLP and transform them using a Transformer block while maintaining a consistent full-resolution image across all bricks. Experimental results demonstrate that LEGO bricks enhance training efficiency, expedite convergence, and facilitate variable-resolution image generation while maintaining strong generative performance. Moreover, LEGO significantly reduces sampling time compared to other methods, establishing it as a valuable enhancement for diffusion models. 
    more » « less
    Free, publicly-accessible full text available May 1, 2025
  2. Abstract The infraorder Brachyura (true or short-tailed crabs) represents a successful group of marine invertebrates yet with limited genomic resources. Here we report a chromosome-anchored reference genome and transcriptomes of the Chinese mitten crab Eriocheir sinensis , a catadromous crab and invasive species with wide environmental tolerance, strong osmoregulatory capacity and high fertility. We show the expansion of specific gene families in the crab, including F-ATPase, which enhances our knowledge on the adaptive plasticity of this successful invasive species. Our analysis of spatio-temporal transcriptomes and the genome of E. sinensis and other decapods shows that brachyurization development is associated with down-regulation of Hox genes at the megalopa stage when tail shortening occurs. A better understanding of the molecular mechanism regulating sexual development is achieved by integrated analysis of multiple omics. These genomic resources significantly expand the gene repertoire of Brachyura, and provide insights into the biology of this group, and Crustacea in general. 
    more » « less
  3. Sentiment analysis on large-scale social media data is important to bridge the gaps between social media contents and real world activities including political election prediction, individual and public emotional status monitoring and analysis, and so on. Although textual sentiment analysis has been well studied based on platforms such as Twitter and Instagram, analysis of the role of extensive emoji uses in sentiment analysis remains light. In this paper, we propose a novel scheme for Twitter sentiment analysis with extra attention on emojis.We first learn bi-sense emoji embeddings under positive and negative sentimental tweets individually, and then train a sentiment classifier by attending on these bi-sense emoji embeddings with an attention-based long short-term memory network (LSTM). Our experiments show that the bi-sense embedding is effective for extracting sentiment-aware embeddings of emojis and outperforms the state-of-the-art models. We also visualize the attentions to show that the bi-sense emoji embedding provides better guidance on the attention mechanism to obtain a more robust understanding of the semantics and sentiments. 
    more » « less