Sarcasm is a nuanced form of human communication characterized by a mismatch between an utterance and the speaker's intent or contextual cues. Recent studies have aimed to advance the understanding of sarcasm by developing systems capable of generating rationales behind sarcastic expressions. In particular, multimodal cues such as facial expressions and vocal tone have been crucial indicators when semantic incongruity with the utterance is prominent. However, existing multimodal sarcasm reasoning approaches fall short of providing fine-grained explanations. Sarcasm can be further categorized into specific subtypes based on the forms of inversion it employs, such as nonverbal cues, dialogue context, and exaggerated word emphasis. To address this, we introduce a novel task called Sarcasm Subtype-specific Reasoning Generation (SSRG). To facilitate research on this task, we present the Sarcasm Subtype-specific Reasoning Dataset (SSRD), which establishes a new benchmark for fine-grained sarcasm reasoning. Through extensive experiments, we demonstrate that leveraging multimodal cues significantly enhances subtype-specific sarcasm reasoning. Moreover, we show that integrating these multimodal cues into textual representations enables strong performance even when using only large language models (LLMs).

Thermal optimization plays a crucial role in the design of advanced systems in package. Due to the large number of thermal simulations needed for full design space exploration, reductions in simulation run-time are critical. Here, we propose a data-driven approach to physics simulation by using neural networks (NNs) to cast the temperature solution process into an image-to-image translation problem. We first model the power generation map, conductivity map, and boundary conditions (BCs) into separate channels of an image. We then generate temperature solutions by training a generative adversarial network, composed of a U-Net shaped generator and a discriminator. The resultant NN model can handle diverse thermal simulation scenarios with accuracy. More importantly, our model can handle BCs, power maps, and physical package designs which are unseen during the training. Experiments show that speed wise, it enables near real-time design, providing a$2581\times $and$9171\times $speedup over a custom sparse matrix optimized finite element method and ABAQUS, respectively. Comparisons with state-of-the-art methods have demonstrated the accuracy, efficiency, and versatility of the proposed work.

Seungjong Sun, Eungu Lee, Seo Yeon Baek, Seunghyun Hwang, Wonbyung Lee, Dongyan Nan, Bernard J Jansen, Jang Hyun Kim. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher network at the deployment stage. To reduce the necessity of training a large teacher model, the recent literatures introduced a self-knowledge distillation, which trains a student network progressively to distill its own knowledge without a pretrained teacher network. While Self-knowledge distillation is largely divided into a data augmentation based approach and an auxiliary network based approach, the data augmentation approach looses its local information in the augmentation process, which hinders its applicability to diverse vision tasks, such as semantic segmentation. Moreover, these knowledge distillation approaches do not receive the refined feature maps, which are prevalent in the object detection and semantic segmentation community. This paper proposes a novel self-knowledge distillation method, Feature Refinement via Self-Knowledge Distillation (FRSKD), which utilizes an auxiliary self-teacher network to transfer a refined knowledge for the classifier network. Our proposed method, FRSKD, can utilize both soft label and feature-map distillations for the self-knowledge distillation. Therefore, FRSKD can be applied to classification, and semantic segmentation, which emphasize preserving the local information. We demonstrate the effectiveness of FRSKD by enumerating its performance improvements in diverse tasks and benchmark datasets. The implemented code is available at https://github.com/MingiJi/FRSKD.

In this paper, we model the subspace of convolutional filters with a neural ordinary differential equation (ODE) to enable gradual changes in generated images. Decomposing convolutional filters over a set of filter atoms allows efficiently modeling and sampling from a subspace of high-dimensional filters. By further modeling filters atoms with a neural ODE, we show both empirically and theoretically that such introduced continuity can be propagated to the generated images, and thus achieves gradually evolved image generation. We support the proposed framework of image generation with continuous filter atoms using various experiments, including image-to-image translation and image generation conditioned on continuous labels. Without auxiliary network components and heavy supervision, the proposed continuous filter atoms allow us to easily manipulate the gradual change of generated images by controlling integration intervals of neural ordinary differential equation. This research sheds the light on using the subspace of network parameters to navigate the diverse appearance of image generation.

The US domestic air passenger transportation is one of the largest markets worldwide.Optimally allocating flights to the US domestic airways (i.e., air routes) is essential in maximizing the revenue of airlines and many research works have been proposed to improve their market shares/profits.Most proposed methods, however, suffer from a lack of scalability; even state-of-the-art methods demonstrate their performance with only tens of routes.To address this shortcoming, we propose a novel unified framework to integrate the market share prediction model and the frequency optimization module, which significantly improves the scalability of the entire framework.By design, our proposed prediction model is concave w.r.t.flight frequency and its gradients are Lipschitz continuous.Exploiting these two properties allows us to use an alternating direction method of multipliers (ADMM)-based optimization technique, which quickly solves a large-scale frequency optimization problem with guaranteed global convergence.Our proposed method is able to solve a problem whose search space size is O(n 700 ) (vs.O(n 30 ) in existing works).