Search

Latent representation alignment has become a foundational technique for constructing multimodal large language models (MLLM) by mapping embeddings from different modalities into a shared space, often aligned with the embedding space of large language models (LLMs) to enable effective cross-modal understanding. While preliminary protein-focused MLLMs have emerged, they have predominantly relied on heuristic approaches, lacking a fundamental understanding of optimal alignment practices across representations. In this study, we explore the alignment of multimodal representations between LLMs and Geometric Deep Models (GDMs) in the protein domain. We comprehensively evaluate three state-of-the-art LLMs (Gemma2-2B, LLaMa3.1-8B, and LLaMa3.1-70B) with four protein-specialized GDMs (GearNet, GVP, ScanNet, GAT). Our work examines alignment factors from both model and protein perspectives, identifying challenges in current alignment methodologies and proposing strategies to improve the alignment process. Our key findings reveal that GDMs incorporating both graph and 3D structural information align better with LLMs, larger LLMs demonstrate improved alignment capabilities, and protein rarity significantly impacts alignment performance. We also find that increasing GDM embedding dimensions, using two-layer projection heads, and fine-tuning LLMs on protein-specific data substantially enhance alignment quality. These strategies offer potential enhancements to the performance of protein-related multimodal models. Our code and data are available at https://github.com/Tizzzzy/LLM-GDM-alignment., Comment: 24 pages, 9 figures

In this paper, we present an acoustic vortex filter (AVF) based on tunable metasurfaces, which can selectively filter the incident multiplexed vortices that carry different orbital angular momentum (OAM). Our metasurface-based AVF is composed of an upper acoustic metasurface (UAM) and a lower acoustic metasurface (LAM), of which the intrinsic topological charge (ITC) can be tuned by mechanically rotating the UAM along its central axis. Due to the critical order of the propagating vortex modes in waveguide, controlling the ITC of the AVF allows for the selective filtering of incoming multiplexed acoustic vortex beams based on the sound vortex diffraction in phase-gradient metasurface, which endows the vortex filter the capability that let the incident vortex of specific OAM pass through it. In the following demonstration, both in theory and experiment, we design the AVF and effectively filter the acoustic vortices with two opposite topological charges (TCs) by simply altering the orientation angle of the UAM. Based on this, we further demonstrate its application in asymmetric acoustic wave transmission. Our work offers an approach to selectively filter the incident acoustic vortex, which improves the capability to control the acoustic OAM via metasurfaces., Comment: 7 pages, 6 figures

We propose a strategy to continuously tune the amplitude of acoustic waves based on the interference among two mode-conversion paths in passive acoustic structures. The interference phenomenon is attributed to two conjugate acoustic geometric phases obtained with two mode-conversion processes in hybrid-type geometric-phase meta-atom (HGPM) pair. Notably, 100% modulation depth of the wave amplitude is achievable by simply varying the local orientation angle of meta-atom. We utilize the acoustic structure made of two cylindrical resonators to construct deep-subwavelength secondary source with designated initial phase delay, and HGPM supporting desired mode-conversion functionality is accordingly fabricated with four secondary sources. Both theory and experiment consistently verify the continuous amplitude modulation function of HGPM pair, which showcases a general scheme for reconfigurable amplitude-type acoustic meta-devices, i.e., those that require grayscale amplitude modulation for acoustic field engineering., Comment: 16 pages, 4 figures

Unsupervised Anomalous Sound Detection (ASD) aims to design a generalizable method that can be used to detect anomalies when only normal sounds are given. In this paper, Anomalous Sound Detection based on Diffusion Models (ASD-Diffusion) is proposed for ASD in real-world factories. In our pipeline, the anomalies in acoustic features are reconstructed from their noisy corrupted features into their approximate normal pattern. Secondly, a post-processing anomalies filter algorithm is proposed to detect anomalies that exhibit significant deviation from the original input after reconstruction. Furthermore, denoising diffusion implicit model is introduced to accelerate the inference speed by a longer sampling interval of the denoising process. The proposed method is innovative in the application of diffusion models as a new scheme. Experimental results on the development set of DCASE 2023 challenge task 2 outperform the baseline by 7.75%, demonstrating the effectiveness of the proposed method., Comment: This paper will appear at ICPR 2024

State-of-the-art (SOTA) video denoising methods employ multi-frame simultaneous denoising mechanisms, resulting in significant delays (e.g., 16 frames), making them impractical for real-time cameras. To overcome this limitation, we propose a multi-fusion gated recurrent Transformer network (GRTN) that achieves SOTA denoising performance with only a single-frame delay. Specifically, the spatial denoising module extracts features from the current frame, while the reset gate selects relevant information from the previous frame and fuses it with current frame features via the temporal denoising module. The update gate then further blends this result with the previous frame features, and the reconstruction module integrates it with the current frame. To robustly compute attention for noisy features, we propose a residual simplified Swin Transformer with Euclidean distance (RSSTE) in the spatial and temporal denoising modules. Comparative objective and subjective results show that our GRTN achieves denoising performance comparable to SOTA multi-frame delay networks, with only a single-frame delay., Comment: 5 pages, 5 figures

Prompt engineering is critical for effective interaction with large language models (LLMs) such as ChatGPT. However, efforts to teach this skill to students have been limited. This study designed and implemented a prompt engineering intervention, examining its influence on undergraduate students' AI self-efficacy, AI knowledge, and proficiency in creating effective prompts. The intervention involved 27 students who participated in a 100-minute workshop conducted during their history course at a university in Hong Kong. During the workshop, students were introduced to prompt engineering strategies, which they applied to plan the course's final essay task. Multiple data sources were collected, including students' responses to pre- and post-workshop questionnaires, pre- and post-workshop prompt libraries, and written reflections. The study's findings revealed that students demonstrated a higher level of AI self-efficacy, an enhanced understanding of AI concepts, and improved prompt engineering skills because of the intervention. These findings have implications for AI literacy education, as they highlight the importance of prompt engineering training for specific higher education use cases. This is a significant shift from students haphazardly and intuitively learning to engineer prompts. Through prompt engineering education, educators can faciitate students' effective navigation and leverage of LLMs to support their coursework., Comment: 34 pages, 6 figures

Large Language Models (LLMs) have demonstrated remarkable performance across various natural language processing tasks. Recently, several LLMs-based pipelines have been developed to enhance learning on graphs with text attributes, showcasing promising performance. However, graphs are well-known to be susceptible to adversarial attacks and it remains unclear whether LLMs exhibit robustness in learning on graphs. To address this gap, our work aims to explore the potential of LLMs in the context of adversarial attacks on graphs. Specifically, we investigate the robustness against graph structural and textual perturbations in terms of two dimensions: LLMs-as-Enhancers and LLMs-as-Predictors. Through extensive experiments, we find that, compared to shallow models, both LLMs-as-Enhancers and LLMs-as-Predictors offer superior robustness against structural and textual attacks.Based on these findings, we carried out additional analyses to investigate the underlying causes. Furthermore, we have made our benchmark library openly available to facilitate quick and fair evaluations, and to encourage ongoing innovative research in this field.

Graph neural networks (GNNs) have exhibited remarkable performance under the assumption that test data comes from the same distribution of training data. However, in real-world scenarios, this assumption may not always be valid. Consequently, there is a growing focus on exploring the Out-of-Distribution (OOD) problem in the context of graphs. Most existing efforts have primarily concentrated on improving graph OOD generalization from two \textbf{model-agnostic} perspectives: data-driven methods and strategy-based learning. However, there has been limited attention dedicated to investigating the impact of well-known \textbf{GNN model architectures} on graph OOD generalization, which is orthogonal to existing research. In this work, we provide the first comprehensive investigation of OOD generalization on graphs from an architecture perspective, by examining the common building blocks of modern GNNs. Through extensive experiments, we reveal that both the graph self-attention mechanism and the decoupled architecture contribute positively to graph OOD generalization. In contrast, we observe that the linear classification layer tends to compromise graph OOD generalization capability. Furthermore, we provide in-depth theoretical insights and discussions to underpin these discoveries. These insights have empowered us to develop a novel GNN backbone model, DGAT, designed to harness the robust properties of both graph self-attention mechanism and the decoupled architecture. Extensive experimental results demonstrate the effectiveness of our model under graph OOD, exhibiting substantial and consistent enhancements across various training strategies.

Integrated quantum light source is increasingly desirable in large-scale quantum information processing.~Despite recent remarkable advances, new material platform is constantly being explored for the fully on-chip integration of quantum light generation, active and passive manipulation, and detection. Here, for the first time, we demonstrate a gallium nitride (GaN) microring based quantum light generation in the telecom C-band, which has potential towards the monolithic integration of quantum light source.~In our demonstration, the GaN microring has a free spectral range of 330 GHz and a near-zero anomalous dispersion region of over 100 nm. The generation of energy-time entangled photon pair is demonstrated with a typical raw two-photon interference visibility of 95.5$\pm$6.5%, which is further configured to generate heralded single photon with a typical heralded second-order auto-correlation $g^{(2)}_{H}(0)$ of 0.045$\pm$0.001. Our results pave the way for developing chip-scale quantum photonic circuit.

With the development of new Internet services such as computation-intensive and delay-sensitive tasks, the traditional "Best Effort" network transmission mode has been greatly challenged. The network system is urgently required to provide end-to-end transmission determinacy and computing determinacy for new applications to ensure the safe and efficient operation of services. Based on the research of the convergence of computing and networking, a new network paradigm named deterministic computing power networking (Det-CPN) is proposed. In this article, we firstly introduce the research advance of computing power networking. And then the motivations and scenarios of Det-CPN are analyzed. Following that, we present the system architecture, technological capabilities, workflow as well as key technologies for Det-CPN. Finally, the challenges and future trends of Det-CPN are analyzed and discussed.

China Spallation Neutron Source(CSNS) target power will upgrade to 500 kW(CSNS-II) from 300kW, energy gain of H-Linac will up to 300 MeV from 80 MeV using about 50 superconductor cavities. LLRF is an important device for controlling the amplitude and phase of the SRF cavity field to be less than 0.6% and 0.6 deg. The parameters and requirements for CSNS-II Linac LLRF are presented here. The preliminary design work and algorithm verification progress and results at C-ADS Injector-I are introduced., Comment: Talk presented at LLRF Workshop 2023(LLRF2023, arXiv:2310.03199)

In this work, we utilize thin dielectric meta-atoms placed on a silver substrate to efficiently enhance and manipulate the third harmonic generation. We theoretically and experimentally reveal that when the structural symmetry of the meta-atom is incompatible with the lattice symmetry of an array, some generalized nonlinear geometric phases appear, which offers new possibilities for harmonic generation control beyond the accessible symmetries governed by the selection rule. The underlying mechanism is attributed to the modified rotation of the effective principal axis of a dense meta-atom array, where the strong coupling among the units gives rise to a generalized linear geometric phase modulation on the pump light. Therefore, nonlinear geometric phases carried by the third-harmonic emissions are the natural result of the wave-mixing process among the modes excited at the fundamental frequency. This mechanism further points out a new strategy to predict the nonlinear geometric phases delivered by the nanostructures according to their linear responses. Our design is simple and efficient, and offers alternatives for the nonlinear meta-devices that are capable of flexible photon generation and manipulation.

This study applies Activity Theory and investigates the attitudes and contradictions of 67 English as a foreign language (EFL) students from four Hong Kong secondary schools towards machine-in-the-loop writing, where artificial intelligence (AI) suggests ideas during composition. Students answered an open-ended question about their feelings on writing with AI. Results revealed mostly positive attitudes, with some negative or mixed feelings. From a thematic analysis, contradictions or points of tension between students and AI stemmed from AI inadequacies, students' balancing enthusiasm with preference, and their striving for language autonomy. The research highlights the benefits and challenges of implementing machine-in-the-loop writing in EFL classrooms, suggesting educators align activity goals with students' values, language abilities, and AI capabilities to enhance students' activity systems., Comment: 38 pages, 4 figures

ChatGPT is a state-of-the-art (SOTA) chatbot. Although it has potential to support English as a foreign language (EFL) students' writing, to effectively collaborate with it, a student must learn to engineer prompts, that is, the skill of crafting appropriate instructions so that ChatGPT produces desired outputs. However, writing an appropriate prompt for ChatGPT is not straightforward for non-technical users who suffer a trial-and-error process. This paper examines the content of EFL students' ChatGPT prompts when completing a writing task and explores patterns in the quality and quantity of the prompts. The data come from iPad screen recordings of secondary school EFL students who used ChatGPT and other SOTA chatbots for the first time to complete the same writing task. The paper presents a case study of four distinct pathways that illustrate the trial-and-error process and show different combinations of prompt content and quantity. The cases contribute evidence for the need to provide prompt engineering education in the context of the EFL writing classroom, if students are to move beyond an individual trial-and-error process, learning a greater variety of prompt content and more sophisticated prompts to support their writing., Comment: 41 pages, 6 figures

This study applies Activity Theory to investigate how English as a foreign language (EFL) students prompt generative artificial intelligence (AI) tools during short story writing. Sixty-seven Hong Kong secondary school students created generative-AI tools using open-source language models and wrote short stories with them. The study collected and analyzed the students' generative-AI tools, short stories, and written reflections on their conditions or purposes for prompting. The research identified three main themes regarding the purposes for which students prompt generative-AI tools during short story writing: a lack of awareness of purposes, overcoming writer's block, and developing, expanding, and improving the story. The study also identified common characteristics of students' activity systems, including the sophistication of their generative-AI tools, the quality of their stories, and their school's overall academic achievement level, for their prompting of generative-AI tools for the three purposes during short story writing. The study's findings suggest that teachers should be aware of students' purposes for prompting generative-AI tools to provide tailored instructions and scaffolded guidance. The findings may also help designers provide differentiated instructions for users at various levels of story development when using a generative-AI tool., Comment: 44 pages, 9 figures