Shuo Zhang

Shuo Zhang, Boci Peng, Xinping Zhao et al.

The e-commerce platform has evolved rapidly due to its widespread popularity and convenience. Developing an e-commerce shopping assistant for customers is crucial to aiding them in quickly finding desired products and recommending precisely what they need. However, most previous shopping assistants face two main problems: (1) task-specificity, which necessitates the development of different models for various tasks, thereby increasing development costs and limiting effectiveness; and (2) poor generalization, where the trained model performs inadequately on up-to-date products. To resolve these issues, we employ Large Language Models (LLMs) to construct an omnipotent assistant, leveraging their adeptness at handling multiple tasks and their superior generalization capability. Nonetheless, LLMs lack inherent knowledge of e-commerce concepts. To address this, we create an instruction dataset comprising 65,000 samples and diverse tasks, termed as EshopInstruct. Through instruction tuning on our dataset, the assistant, named LLaSA, demonstrates the potential to function as an omnipotent assistant. Additionally, we propose various inference optimization strategies to enhance performance with limited inference resources. In the Amazon KDD Cup 2024 Challenge, our proposed method, LLaSA, achieved an overall ranking of 3rd place on ShopBench, including 57 tasks and approximately 20,000 questions, and we secured top-5 rankings in each track, especially in track4, where we achieved the best performance result among all student teams. Our extensive practices fully demonstrate that LLMs possess the great potential to be competent e-commerce shopping assistants.

Khalid Alnajjar, Mika Hämäläinen, Shuo Zhang

We present the first openly available multimodal metaphor annotated corpus. The corpus consists of videos including audio and subtitles that have been annotated by experts. Furthermore, we present a method for detecting metaphors in the new dataset based on the textual content of the videos. The method achieves a high F1-score (62\%) for metaphorical labels. We also experiment with other modalities and multimodal methods; however, these methods did not out-perform the text-based model. In our error analysis, we do identify that there are cases where video could help in disambiguating metaphors, however, the visual cues are too subtle for our model to capture. The data is available on Zenodo.

Tornike Karchkhadze, Mohammad Rasool Izadi, Shuo Zhang et al.

In this work, we propose an approach to music source separation that uses a generative diffusion model as a last-stage refinement on top of a deterministic separator, progressively enhancing the separated sources through iterative denoising. While the diffusion refinement yields measurable quality gains, it requires iterative steps at inference, increasing computational cost. To speed up the inference process, we apply consistency distillation, reducing inference to a single step while maintaining quality; with two or more steps, the distilled model even surpasses the diffusion-based approach. Crucially, our method is architecture-agnostic: we demonstrate state-of-the-art results when applied to both a custom U-Net-based separator on Slakh2100 and the state-of-the-art BS-RoFormer model on MUSDB18, showing that the refinement generalizes across backbone architectures. Sound examples are available at: https://consistency-separation.github.io/.

Shuo Zhang, Biao Yang, Zhang Li et al.

While large multi-modal models (LMM) have shown notable progress in multi-modal tasks, their capabilities in tasks involving dense textual content remains to be fully explored. Dense text, which carries important information, is often found in documents, tables, and product descriptions. Understanding dense text enables us to obtain more accurate information, assisting in making better decisions. To further explore the capabilities of LMM in complex text tasks, we propose the DT-VQA dataset, with 170k question-answer pairs. In this paper, we conduct a comprehensive evaluation of GPT4V, Gemini, and various open-source LMMs on our dataset, revealing their strengths and weaknesses. Furthermore, we evaluate the effectiveness of two strategies for LMM: prompt engineering and downstream fine-tuning. We find that even with automatically labeled training datasets, significant improvements in model performance can be achieved. We hope that this research will promote the study of LMM in dense text tasks. Code will be released at https://github.com/Yuliang-Liu/MultimodalOCR.

Haijun Yu, Shuo Zhang

Deep neural network approaches show promise in solving partial differential equations. However, unlike traditional numerical methods, they face challenges in enforcing essential boundary conditions. The widely adopted penalty-type methods, for example, offer a straightforward implementation but introduces additional complexity due to the need for hyper-parameter tuning; moreover, the use of a large penalty parameter can lead to artificial extra stiffness, complicating the optimization process. In this paper, we propose a novel, intrinsic approach to impose essential boundary conditions through a framework inspired by intrinsic structures. We demonstrate the effectiveness of this approach using the deep Ritz method applied to Poisson problems, with the potential for extension to more general equations and other deep learning techniques. Numerical results are provided to substantiate the efficiency and robustness of the proposed method.

Shuo Zhang, Jian K. Liu

Protein language models (PLMs) are capable of learning the relationships between protein sequences and functions by treating amino acid sequences as textual data in a self-supervised manner. However, fine-tuning these models typically demands substantial computational resources and time, with results that may not always be optimized for specific tasks. To overcome these challenges, this study employs the LoRA method to perform end-to-end fine-tuning of the ESM-2 model specifically for protein property prediction tasks, utilizing only sequence information. Additionally, a multi-head attention mechanism is integrated into the downstream network to combine sequence features with contact map information, thereby enhancing the model's comprehension of protein sequences. Experimental results of extensive classification and regression tasks demonstrate that the fine-tuned model achieves strong performance and faster convergence across multiple regression and classification tasks.

Xinkai Wang, Shuo Zhang, Ziyi Zhao et al.

While tangible user interface has shown its power in naturally interacting with rigid or soft objects, users cannot conveniently use different types of granular materials as the interaction media. We introduce DipMe as a smart device to recognize the types of granular media in real time, which can be used to connect the granular materials in the physical world with various virtual content. Other than vision-based solutions, we propose a dip operation of our device and exploit the haptic signals to recognize different types of granular materials. With modern machine learning tools, we find the haptic signals from different granular media are distinguishable by DipMe. With the online granular object recognition, we build several tangible interactive applications, demonstrating the effects of DipMe in perceiving granular materials and its potential in developing a tangible user interface with granular objects as the new media.

T. Aleksandra Ma, Sile Yin, Li-Chia Yang et al.

We present a live demonstration for RAVEN, a real-time audio-visual speech enhancement system designed to run entirely on a CPU. In single-channel, audio-only settings, speech enhancement is traditionally approached as the task of extracting clean speech from environmental noise. More recent work has explored the use of visual cues, such as lip movements, to improve robustness, particularly in the presence of interfering speakers. However, to our knowledge, no prior work has demonstrated an interactive system for real-time audio-visual speech enhancement operating on CPU hardware. RAVEN fills this gap by using pretrained visual embeddings from an audio-visual speech recognition model to encode lip movement information. The system generalizes across environmental noise, interfering speakers, transient sounds, and even singing voices. In this demonstration, attendees will be able to experience live audio-visual target speech enhancement using a microphone and webcam setup, with clean speech playback through headphones.

Shuo Zhang

In spontaneous speech, Mandarin tones that belong to the same tone category may exhibit many different contour shapes. We explore the use of data mining and NLP techniques for understanding the variability of tones in a large corpus of Mandarin newscast speech. First, we adapt a graph-based approach to characterize the clusters (fuzzy types) of tone contour shapes observed in each tone n-gram category. Second, we show correlations between these realized contour shape types and a bag of automatically extracted linguistic features. We discuss the implications of the current study within the context of phonological and information theory.