Search

TIPO (Text to Image with text pre-sampling for Prompt Optimization) is an innovative framework designed to enhance text-to-image (T2I) generation by language model (LM) for automatic prompt engineering. By refining and extending user-provided prompts, TIPO bridges the gap between simple inputs and the detailed prompts required for high-quality image generation. Unlike previous approaches that rely on Large Language Models (LLMs) or reinforcement learning (RL), TIPO adjusts user input prompts with the distribution of a trained prompt dataset, eliminating the need for complex runtime cost via lightweight model. This pre-sampling approach enables efficient and scalable prompt optimization, grounded in the model's training distribution. Experimental results demonstrate TIPO's effectiveness in improving aesthetic scores, reducing image corruption, and better aligning generated images with dataset distributions. These findings highlight the critical role of prompt engineering in T2I systems and open avenues for broader applications of automatic prompt refinement., Comment: 21 pages, 13 figures

Goal-oriented chatbots are essential for automating user tasks, such as booking flights or making restaurant reservations. A key component of these systems is Dialogue State Tracking (DST), which interprets user intent and maintains the dialogue state. However, existing DST methods often rely on fixed ontologies and manually compiled slot values, limiting their adaptability to open-domain dialogues. We propose a novel approach that leverages instruction tuning and advanced prompt strategies to enhance DST performance, without relying on any predefined ontologies. Our method enables Large Language Model (LLM) to infer dialogue states through carefully designed prompts and includes an anti-hallucination mechanism to ensure accurate tracking in diverse conversation contexts. Additionally, we employ a Variational Graph Auto-Encoder (VGAE) to model and predict subsequent user intent. Our approach achieved state-of-the-art with a JGA of 42.57% outperforming existing ontology-less DST models, and performed well in open-domain real-world conversations. This work presents a significant advancement in creating more adaptive and accurate goal-oriented chatbots., Comment: There are 10 chapters, including references, and 2 figures used. To be presented at the 15th IEEE International Conference on Knowledge Graphs (ICKG2024)

Papers, patents, and clinical trials are indispensable types of scientific literature in biomedicine, crucial for knowledge sharing and dissemination. However, these documents are often stored in disparate databases with varying management standards and data formats, making it challenging to form systematic, fine-grained connections among them. To address this issue, we introduce PKG2.0, a comprehensive knowledge graph dataset encompassing over 36 million papers, 1.3 million patents, and 0.48 million clinical trials in the biomedical field. PKG2.0 integrates these previously dispersed resources through various links, including biomedical entities, author networks, citation relationships, and research projects. Fine-grained biomedical entity extraction, high-performance author name disambiguation, and multi-source citation integration have played a crucial role in the construction of the PKG dataset. Additionally, project data from the NIH Exporter enriches the dataset with metadata of NIH-funded projects and their scholarly outputs. Data validation demonstrates that PKG2.0 excels in key tasks such as author disambiguation and biomedical entity recognition. This dataset provides valuable resources for biomedical researchers, bibliometric scholars, and those engaged in literature mining., Comment: 31 pages, 6 figures, 22 tables

In this work, we share the insights for achieving state-of-the-art quality in our text-to-image anime image generative model, called Illustrious. To achieve high resolution, dynamic color range images, and high restoration ability, we focus on three critical approaches for model improvement. First, we delve into the significance of the batch size and dropout control, which enables faster learning of controllable token based concept activations. Second, we increase the training resolution of images, affecting the accurate depiction of character anatomy in much higher resolution, extending its generation capability over 20MP with proper methods. Finally, we propose the refined multi-level captions, covering all tags and various natural language captions as a critical factor for model development. Through extensive analysis and experiments, Illustrious demonstrates state-of-the-art performance in terms of animation style, outperforming widely-used models in illustration domains, propelling easier customization and personalization with nature of open source. We plan to publicly release updated Illustrious model series sequentially as well as sustainable plans for improvements.

Quantitative analysis of microstructural features on the nanoscale, including precipitates, local chemical orderings (LCOs) or structural defects (e.g. stacking faults) plays a pivotal role in understanding the mechanical and physical responses of engineering materials. Atom probe tomography (APT), known for its exceptional combination of chemical sensitivity and sub-nanometer resolution, primarily identifies microstructures through compositional segregations. However, this fails when there is no significant segregation, as can be the case for LCOs and stacking faults. Here, we introduce a 3D deep learning approach, AtomNet, designed to process APT point cloud data at the single-atom level for nanoscale microstructure extraction, simultaneously considering compositional and structural information. AtomNet is showcased in segmenting L12-type nanoprecipitates from the matrix in an AlLiMg alloy, irrespective of crystallographic orientations, which outperforms previous methods. AtomNet also allows for 3D imaging of L10-type LCOs in an AuCu alloy, a challenging task for conventional analysis due to their small size and subtle compositional differences. Finally, we demonstrate the use of AtomNet for revealing 2D stacking faults in a Co-based superalloy, without any defected training data, expanding the capabilities of APT for automated exploration of hidden microstructures. AtomNet pushes the boundaries of APT analysis, and holds promise in establishing precise quantitative microstructure-property relationships across a diverse range of metallic materials.

The VR industry is one of the most promising industries for the near future, as it can provide a more immersive connection between people and the virtual world. Currently, VR devices interact with people using inconvenient controllers or cameras that perform poorly in dark environments. Interaction through millimeter-wave wearable devices has the potential to conveniently track human behavior regardless of the lighting conditions. In this study, a millimeter-wave wearable antenna was developed, opening up the possibility for more immersive interaction with VR devices. The antenna features a low loss tangent polyester fabric to minimize dielectric losses and a smooth coating to reduce losses due to rough surfaces. The antenna operates in the 24GHz ISM band, with an S11 value of -29dB at 24.15GHz.

The emergence of various adapters, including Low-Rank Adaptation (LoRA) applied from the field of natural language processing, has allowed diffusion models to personalize image generation at a low cost. However, due to the various challenges including limited datasets and shortage of regularization and computation resources, adapter training often results in unsatisfactory outcomes, leading to the corruption of the backbone model's prior knowledge. One of the well known phenomena is the loss of diversity in object generation, especially within the same class which leads to generating almost identical objects with minor variations. This poses challenges in generation capabilities. To solve this issue, we present Contrastive Adapter Training (CAT), a simple yet effective strategy to enhance adapter training through the application of CAT loss. Our approach facilitates the preservation of the base model's original knowledge when the model initiates adapters. Furthermore, we introduce the Knowledge Preservation Score (KPS) to evaluate CAT's ability to keep the former information. We qualitatively and quantitatively compare CAT's improvement. Finally, we mention the possibility of CAT in the aspects of multi-concept adapter and optimization., Comment: CVPRW 2024

We show that $L^2$-accurate score estimation, in the absence of strong assumptions on the data distribution, is computationally hard even when sample complexity is polynomial in the relevant problem parameters. Our reduction builds on the result of Chen et al. (ICLR 2023), who showed that the problem of generating samples from an unknown data distribution reduces to $L^2$-accurate score estimation. Our hard-to-estimate distributions are the "Gaussian pancakes" distributions, originally due to Diakonikolas et al. (FOCS 2017), which have been shown to be computationally indistinguishable from the standard Gaussian under widely believed hardness assumptions from lattice-based cryptography (Bruna et al., STOC 2021; Gupte et al., FOCS 2022)., Comment: 28 pages

Metasurface has recently emerged as an economic solution to expand mmWave coverage. However, their pervasive deployment remains a challenge, mainly due to the difficulty in reaching the tight 260ns NR synchronization requirement and real-time wireless reconfiguration while maintaining multi-year battery life. This paper presents NR-Surface, the first real-time reconfigurable metasurface fully compliant with the NR standard, operating at 242.7 $\mu$W for a 2.1-year lifetime on an AA battery. NR-Surface incorporates (i) a new extremely low-power (14KHz sampling) reconfiguration interface, NarrowBand Packet Unit (NBPU), for synchronization and real-time reconfiguration, and (ii) a highly responsive and low-leakage metasurface designed for low-duty cycled operation, by carefully leveraging the structure and the periodicity of the NR beam management procedure in the NR standard. NR-Surface is prototyped and evaluated end-to-end with NR BS built on srsRAN to demonstrate diverse usage scenarios including multiple NR-Surface per BS, multiple UE per NR-Surface, and 3D beamforming. Around-the-corner UE evaluations showcase NR-Surface efficacy under different user mobility patterns (20.3dB gain) and dynamic blockage (22.2dB gain)., Comment: 17 pages, 28 figures, to be published in NSDI '24

Emotion Recognition in Conversation (ERC) plays a crucial role in enabling dialogue systems to effectively respond to user requests. The emotions in a conversation can be identified by the representations from various modalities, such as audio, visual, and text. However, due to the weak contribution of non-verbal modalities to recognize emotions, multimodal ERC has always been considered a challenging task. In this paper, we propose Teacher-leading Multimodal fusion network for ERC (TelME). TelME incorporates cross-modal knowledge distillation to transfer information from a language model acting as the teacher to the non-verbal students, thereby optimizing the efficacy of the weak modalities. We then combine multimodal features using a shifting fusion approach in which student networks support the teacher. TelME achieves state-of-the-art performance in MELD, a multi-speaker conversation dataset for ERC. Finally, we demonstrate the effectiveness of our components through additional experiments., Comment: NAACL 2024 main conference

The demand for the three-dimensional (3D) integration of electronic components is on a steady rise. The through-silicon-via (TSV) technique emerges as the only viable method for integrating single-crystalline device components in a 3D format, despite encountering significant processing challenges. While monolithic 3D (M3D) integration schemes show promise, the seamless connection of single-crystalline semiconductors without intervening wafers has yet to be demonstrated. This challenge arises from the inherent difficulty of growing single crystals on amorphous or polycrystalline surfaces post the back-end-of-the-line process at low temperatures to preserve the underlying circuitry. Consequently, a practical growth-based solution for M3D of single crystals remains elusive. Here, we present a method for growing single-crystalline channel materials, specifically composed of transition metal dichalcogenides, on amorphous and polycrystalline surfaces at temperatures lower than 400 {\deg}C. Building on this developed technique, we demonstrate the seamless monolithic integration of vertical single-crystalline logic transistor arrays. This accomplishment leads to the development of unprecedented vertical CMOS arrays, thereby constructing vertical inverters. Ultimately, this achievement sets the stage to pave the way for M3D integration of various electronic and optoelectronic hardware in the form of single crystals.

This paper explains all about our RTPS datasets. We collect malicious/benign packet data by injecting attack data in an Unmanned Ground Vehicle (UGV) in the normal state. We assembled the testbed, consisting of UGV, Controller, PC, and Router. We collect this dataset in the UGV part of our testbed. We conducted two types of attack "Command Injection" and "Command Injection with ARP Spoofing" on our testbed. The data collection time is 180, 300, 600, and 1200. The scenario has 30 each on collection time, 240 total. We expect this dataset to contribute to the development of defense technologies like anomaly detection to address security threat issues in ROS2 networks and Fast-DDS implements., Comment: This manuscript is written in Korean. You can download our dataset through our lab: https://ocslab.hksecurity.net/Datasets/rtps-attack-dataset We welcome your comments or feedback. Contact INFO: Dong Young Kim (klgh1256@korea.ac.kr), Huy Kang Kim (cenda@korea.ac.kr)