How do people determine whether non-human entities have thoughts and feelings — an inner mental life? Prior work has proposed that people use compact sets of dimensions (e.g., body-heart-mind) to form beliefs about familiar kinds, but how do they generalize to novel entities? Here we investigate emerging beliefs about the mental capacities of large language models (LLMs) and how those beliefs are shaped by how LLMs are portrayed. Participants (N = 470) watched brief videos that encouraged them to view LLMs as either machines, tools, or companions then took a survey measuring mental capacity attributions. We found that the companion group more strongly endorsed statements regarding a broad array of mental capacities that LLMs might possess relative to the machine and tool groups, suggesting that people's beliefs can be rapidly shaped by context. Our study highlights the need to explore the factors shaping people's beliefs about emerging technologies to promote accurate public understanding.

Recent advancements in text-to-image (T2I) diffusion models have demonstrated their remarkable capability to generate high-quality images from textual prompts. However, increasing research indicates that these models memorize and replicate images from their training data, raising concerns about potential copyright infringement and privacy risks. In our study, we provide a novel perspective to understand this memorization phenomenon by examining its relationship with cross-attention mechanisms. We reveal that during memorization, the cross-attention tends to focus disproportionately on the embeddings of specific tokens. The diffusion model is overfitted to these token embeddings, memorizing corresponding training images. To elucidate this phenomenon, we further identify and discuss various intrinsic findings of cross-attention that contribute to memorization. Building on these insights, we introduce an innovative approach to detect and mitigate memorization in diffusion models. The advantage of our proposed method is that it will not compromise the speed of either the training or the inference processes in these models while preserving the quality of generation. Our code is available at github.com/renjie3/MemAttn.

Recent technological advancements have enabled spatially resolved transcriptomic profiling but at a multicellular resolution that is more cost-effective. The task of cell type deconvolution has been introduced to disentangle discrete cell types from such multicellular spots. However, existing benchmark datasets for cell type deconvolution are either generated from simulation or limited in scale, predominantly encompassing data on mice and are not designed for human immuno-oncology. To overcome these limitations and promote comprehensive investigation of cell type deconvolution for human immuno-oncology, we introduce a large-scale spatial transcriptomic deconvolution benchmark dataset named SpatialCTD, encompassing 1.8 million cells and 12,900 pseudo spots from the human tumor microenvironment across the lung, kidney, and liver. In addition, SpatialCTD provides more realistic reference than those generated from single-cell RNA sequencing (scRNA-seq) data for most reference-based deconvolution methods. To utilize the location-aware SpatialCTD reference, we propose a graph neural network-based deconvolution method (i.e., GNNDeconvolver). Extensive experiments show that GNNDeconvolver often outperforms existing state-of-the-art methods by a substantial margin, without requiring scRNA-seq data. To enable comprehensive evaluations of spatial transcriptomics data from flexible protocols, we provide an online tool capable of converting spatial transcriptomic data from various platforms (e.g., 10x Visium, MERFISH, and sci-Space) into pseudo spots, featuring adjustable spot size. The SpatialCTD dataset and GNNDeconvolver implementation are available at https://github.com/OmicsML/SpatialCTD, and the online converter tool can be accessed at https://omicsml.github.io/SpatialCTD/.

Single-cell technologies are revolutionizing the entire field of biology. The large volumes of data generated by single-cell technologies are high dimensional, sparse, and heterogeneous and have complicated dependency structures, making analyses using conventional machine learning approaches challenging and impractical. In tackling these challenges, deep learning often demonstrates superior performance compared to traditional machine learning methods. In this work, we give a comprehensive survey on deep learning in single-cell analysis. We first introduce background on single-cell technologies and their development, as well as fundamental concepts of deep learning including the most popular deep architectures. We present an overview of the single-cell analytic pipeline pursued in research applications while noting divergences due to data sources or specific applications. We then review seven popular tasks spanning different stages of the singlecell analysis pipeline, including multimodal integration, imputation, clustering, spatial domain identification, cell-type deconvolution, cell segmentation, and cell-type annotation. Under each task, we describe the most recent developments in classical and deep learning methods and discuss their advantages and disadvantages. Deep learning tools and benchmark datasets are also summarized for each task. Finally, we discuss the future directions and the most recent challenges. This survey will serve as a reference for biologists and computer scientists, encouraging collaborations.

Abstract DANCE is the first standard, generic, and extensible benchmark platform for accessing and evaluating computational methods across the spectrum of benchmark datasets for numerous single-cell analysis tasks. Currently, DANCE supports 3 modules and 8 popular tasks with 32 state-of-art methods on 21 benchmark datasets. People can easily reproduce the results of supported algorithms across major benchmark datasets via minimal efforts, such as using only one command line. In addition, DANCE provides an ecosystem of deep learning architectures and tools for researchers to facilitate their own model development. DANCE is an open-source Python package that welcomes all kinds of contributions.

Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain, aiming to develop graph models trained on extensive and diverse data to enhance their applicability across various tasks and domains. Developing GFMs presents unique challenges over traditional Graph Neural Networks (GNNs), which are typically trained from scratch for specific tasks on particular datasets. The primary challenge in constructing GFMs lies in effectively leveraging vast and diverse graph data to achieve positive transfer. Drawing inspiration from existing foundation models in the CV and NLP domains, we propose a novel perspective for the GFM development by advocating for a ``graph vocabulary'', in which the basic transferable units underlying graphs encode the invariance on graphs. We ground the graph vocabulary construction from essential aspects including network analysis, expressiveness, and stability. Such a vocabulary perspective can potentially advance the future GFM design in line with the neural scaling laws. All relevant resources with GFM design can be found here.

Recent research has highlighted the vulnerability of Deep Neural Networks (DNNs) against data poisoning attacks. These attacks aim to inject poisoning samples into the models' training dataset such that the trained models have inference failures. While previous studies have executed different types of attacks, one major challenge that greatly limits their effectiveness is the uncertainty of the re-training process after the injection of poisoning samples, including the re-training initialization or algorithms. To address this challenge, we propose a novel attack method called ''Sharpness-Aware Data Poisoning Attack (SAPA)''. In particular, it leverages the concept of DNNs' loss landscape sharpness to optimize the poisoning effect on the worst re-trained model. It helps enhance the preservation of the poisoning effect, regardless of the specific retraining procedure employed. Extensive experiments demonstrate that SAPA offers a general and principled strategy that significantly enhances various types of poisoning attacks.

The recent development of multimodal single-cell technology has made the possibility of acquiring multiple omics data from individual cells, thereby enabling a deeper understanding of cellular states and dynamics. Nevertheless, the proliferation of multimodal single-cell data also introduces tremendous challenges in modeling the complex interactions among different modalities. The recently advanced methods focus on constructing static interaction graphs and applying graph neural networks (GNNs) to learn from multimodal data. However, such static graphs can be suboptimal as they do not take advantage of the downstream task information; meanwhile GNNs also have some inherent limitations when deeply stacking GNN layers. To tackle these issues, in this work, we investigate how to leverage transformers for multimodal single-cell data in an end-to-end manner while exploiting downstream task information. In particular, we propose a scMoFormer framework which can readily incorporate external domain knowledge and model the interactions within each modality and cross modalities. Extensive experiments demonstrate that scMoFormer achieves superior performance on various benchmark datasets. Remarkably, scMoFormer won a Kaggle silver medal with the rank of 24/1221 (Top 2%) without ensemble in a NeurIPS 2022 competition(1). Our implementation is publicly available at Github(2).

Large language models (LLMs) have show great ability in various natural language tasks. However, there are concerns that LLMs are possible to be used improperly or even illegally. To prevent the malicious usage of LLMs, detecting LLM-generated text becomes crucial in the deployment of LLM applications. Watermarking is an effective strategy to detect the LLM-generated content by encoding a pre-defined secret watermark to facilitate the detection process. However, the majority of existing watermark methods leverage the simple hashes of precedent tokens to partition vocabulary. Such watermark can be easily eliminated by paraphrase and correspondingly the detection effectiveness will be greatly compromised. Thus, to enhance the robustness against paraphrase, we propose a semantics-based watermark framework SemaMark. It leverages the semantics as an alternative to simple hashes of tokens since the paraphrase will likely preserve the semantic meaning of the sentences. Comprehensive experiments are conducted to demonstrate the effectiveness and robustness of SemaMark under different paraphrases.

Recent studies on Graph Neural Networks(GNNs) provide both empirical and theoretical evidence supporting their effectiveness in capturing structural patterns on both homophilic and certain heterophilic graphs. Notably, most real-world homophilic and heterophilic graphs are comprised of a mixture of nodes in both homophilic and heterophilic structural patterns, exhibiting a structural disparity. However, the analysis of GNN performance with respect to nodes exhibiting different structural patterns, e.g., homophilic nodes in heterophilic graphs, remains rather limited. In the present study, we provide evidence that Graph Neural Networks(GNNs) on node classification typically perform admirably on homophilic nodes within homophilic graphs and heterophilic nodes within heterophilic graphs while struggling on the opposite node set, exhibiting a performance disparity. We theoretically and empirically identify effects of GNNs on testing nodes exhibiting distinct structural patterns. We then propose a rigorous, non-i.i.d PAC-Bayesian generalization bound for GNNs, revealing reasons for the performance disparity, namely the aggregated feature distance and homophily ratio difference between training and testing nodes. Furthermore, we demonstrate the practical implications of our new findings via (1) elucidating the effectiveness of deeper GNNs; and (2) revealing an over-looked distribution shift factor on graph out-of-distribution problem and proposing a new scenario accordingly.