Jinyu Liu

Jiashuo Yu, Jinyu Liu, Ying Cheng et al.

Weakly-supervised audio-visual violence detection aims to distinguish snippets containing multimodal violence events with video-level labels. Many prior works perform audio-visual integration and interaction in an early or intermediate manner, yet overlooking the modality heterogeneousness over the weakly-supervised setting. In this paper, we analyze the modality asynchrony and undifferentiated instances phenomena of the multiple instance learning (MIL) procedure, and further investigate its negative impact on weakly-supervised audio-visual learning. To address these issues, we propose a modality-aware contrastive instance learning with self-distillation (MACIL-SD) strategy. Specifically, we leverage a lightweight two-stream network to generate audio and visual bags, in which unimodal background, violent, and normal instances are clustered into semi-bags in an unsupervised way. Then audio and visual violent semi-bag representations are assembled as positive pairs, and violent semi-bags are combined with background and normal instances in the opposite modality as contrastive negative pairs. Furthermore, a self-distillation module is applied to transfer unimodal visual knowledge to the audio-visual model, which alleviates noises and closes the semantic gap between unimodal and multimodal features. Experiments show that our framework outperforms previous methods with lower complexity on the large-scale XD-Violence dataset. Results also demonstrate that our proposed approach can be used as plug-in modules to enhance other networks. Codes are available at https://github.com/JustinYuu/MACIL_SD.

Jianrong Wang, Jinyu Liu, Longxuan Zhao et al.

Acoustic-to-articulatory inversion (AAI) is to obtain the movement of articulators from speech signals. Until now, achieving a speaker-independent AAI remains a challenge given the limited data. Besides, most current works only use audio speech as input, causing an inevitable performance bottleneck. To solve these problems, firstly, we pre-train a speech decomposition network to decompose audio speech into speaker embedding and content embedding as the new personalized speech features to adapt to the speaker-independent case. Secondly, to further improve the AAI, we propose a novel auxiliary feature network to estimate the lip auxiliary features from the above personalized speech features. Experimental results on three public datasets show that, compared with the state-of-the-art only using the audio speech feature, the proposed method reduces the average RMSE by 0.25 and increases the average correlation coefficient by 2.0% in the speaker-dependent case. More importantly, the average RMSE decreases by 0.29 and the average correlation coefficient increases by 5.0% in the speaker-independent case.

Jinyu Liu, Ying Cheng, Yuejie Zhang et al.

Visual-only self-supervised learning has achieved significant improvement in video representation learning. Existing related methods encourage models to learn video representations by utilizing contrastive learning or designing specific pretext tasks. However, some models are likely to focus on the background, which is unimportant for learning video representations. To alleviate this problem, we propose a new view called long-range residual frame to obtain more motion-specific information. Based on this, we propose the Motion-Contrastive Perception Network (MCPNet), which consists of two branches, namely, Motion Information Perception (MIP) and Contrastive Instance Perception (CIP), to learn generic video representations by focusing on the changing areas in videos. Specifically, the MIP branch aims to learn fine-grained motion features, and the CIP branch performs contrastive learning to learn overall semantics information for each instance. Experiments on two benchmark datasets UCF-101 and HMDB-51 show that our method outperforms current state-of-the-art visual-only self-supervised approaches.

Jinyu Liu, Hongye Guo, Qinghu Tang et al.

With the growing penetration of renewable energy resource, electricity market prices have exhibited greater volatility. Therefore, it is important for Energy Storage Systems(ESSs) to leverage the multidimensional nature of energy market bids to maximize profitability. However, current learning methods cannot fully utilize the high-dimensional price-quantity bids in the energy markets. To address this challenge, we modify the common reinforcement learning(RL) process by proposing a new bid representation method called Neural Network Embedded Bids (NNEBs). NNEBs refer to market bids that are represented by monotonic neural networks with discrete outputs. To achieve effective learning of NNEBs, we first learn a neural network as a strategic mapping from the market price to ESS power output with RL. Then, we re-train the network with two training modifications to make the network output monotonic and discrete. Finally, the neural network is equivalently converted into a high-dimensional bid for bidding. We conducted experiments over real-world market datasets. Our studies show that the proposed method achieves 18% higher profit than the baseline and up to 78% profit of the optimal market bidder.

Amanda Nyholm, Yessica Arellano, Jinyu Liu et al.

Reliable flow measurements are essential in many industries, but current instruments often fail to accurately estimate multiphase flows, which are frequently encountered in real-world operations. Combining machine learning (ML) algorithms with accurate single-phase flowmeters has therefore received extensive research attention in recent years. The Coriolis mass flowmeter is a widely used single-phase meter that provides direct mass flow measurements, which ML models can be trained to correct, thereby reducing measurement errors in multiphase conditions. This paper demonstrates that preserving temporal information significantly improves model performance in such scenarios. We compare a multilayer perceptron, a windowed multilayer perceptron, and a convolutional neural network (CNN) on three-phase air-water-oil flow data from 342 experiments. Whereas prior work typically compresses each experiment into a single averaged sample, we instead compute short-time averages from within each experiment and train models that preserve temporal information at several downsampling intervals. The CNN performed best at 0.25 Hz with approximately 95 % of relative errors below 13 %, a normalized root mean squared error of 0.03, and a mean absolute percentage error of approximately 4.3 %, clearly outperforming the best single-averaged model and demonstrating that short-time averaging within individual experiments is preferable. Results are consistent across multiple data splits and random seeds, demonstrating robustness.

Yun Zhou, Yaoting Wang, Guangquan Jie et al.

SAM3D has garnered widespread attention for its strong 3D object reconstruction capabilities. However, a key limitation remains: SAM3D cannot reconstruct specific objects referred to by textual descriptions, a capability that is essential for practical applications such as 3D editing, game development, and virtual environments. To address this gap, we introduce Ref-SAM3D, a simple yet effective extension to SAM3D that incorporates textual descriptions as a high-level prior, enabling text-guided 3D reconstruction from a single RGB image. Through extensive qualitative experiments, we show that Ref-SAM3D, guided only by natural language and a single 2D view, delivers competitive and high-fidelity zero-shot reconstruction performance. Our results demonstrate that Ref-SAM3D effectively bridges the gap between 2D visual cues and 3D geometric understanding, offering a more flexible and accessible paradigm for reference-guided 3D reconstruction. Code is available at: https://github.com/FudanCVL/Ref-SAM3D.

Eric Khiu, Hasti Toossi, David Anugraha et al.

Fine-tuning and testing a multilingual large language model is expensive and challenging for low-resource languages (LRLs). While previous studies have predicted the performance of natural language processing (NLP) tasks using machine learning methods, they primarily focus on high-resource languages, overlooking LRLs and shifts across domains. Focusing on LRLs, we investigate three factors: the size of the fine-tuning corpus, the domain similarity between fine-tuning and testing corpora, and the language similarity between source and target languages. We employ classical regression models to assess how these factors impact the model's performance. Our results indicate that domain similarity has the most critical impact on predicting the performance of Machine Translation models.

Hasti Toossi, Guo Qing Huai, Jinyu Liu et al.

In the pursuit of supporting more languages around the world, tools that characterize properties of languages play a key role in expanding the existing multilingual NLP research. In this study, we focus on a widely used typological knowledge base, URIEL, which aggregates linguistic information into numeric vectors. Specifically, we delve into the soundness and reproducibility of the approach taken by URIEL in quantifying language similarity. Our analysis reveals URIEL's ambiguity in calculating language distances and in handling missing values. Moreover, we find that URIEL does not provide any information about typological features for 31\% of the languages it represents, undermining the reliabilility of the database, particularly on low-resource languages. Our literature review suggests URIEL and lang2vec are used in papers on diverse NLP tasks, which motivates us to rigorously verify the database as the effectiveness of these works depends on the reliability of the information the tool provides.

Jinyu Liu, Hongye Guo, Yun Li et al.

Over the past decade, bidding in power markets has attracted widespread attention. Reinforcement Learning (RL) has been widely used for power market bidding as a powerful AI tool to make decisions under real-world uncertainties. However, current RL methods mostly employ low dimensional bids, which significantly diverge from the N price-power pairs commonly used in the current power markets. The N-pair bidding format is denoted as High Dimensional Bids (HDBs), which has not been fully integrated into the existing RL-based bidding methods. The loss of flexibility in current RL bidding methods could greatly limit the bidding profits and make it difficult to tackle the rising uncertainties brought by renewable energy generations. In this paper, we intend to propose a framework to fully utilize HDBs for RL-based bidding methods. First, we employ a special type of neural network called Neural Network Supply Functions (NNSFs) to generate HDBs in the form of N price-power pairs. Second, we embed the NNSF into a Markov Decision Process (MDP) to make it compatible with most existing RL methods. Finally, experiments on Energy Storage Systems (ESSs) in the PJM Real-Time (RT) power market show that the proposed bidding method with HDBs can significantly improve bidding flexibility, thereby improving the profit of the state-of-the-art RL bidding methods.

Jinyu Liu, Gaoyang Zhang, Yang Zhou et al.

Nasotracheal intubation (NTI) is a vital procedure in emergency airway management, where rapid and accurate glottis detection is essential to ensure patient safety. However, existing machine assisted visual detection systems often rely on high performance computational resources and suffer from significant inference delays, which limits their applicability in time critical and resource constrained scenarios. To overcome these limitations, we propose Mobile GlottisNet, a lightweight and efficient glottis detection framework designed for real time inference on embedded and edge devices. The model incorporates structural awareness and spatial alignment mechanisms, enabling robust glottis localization under complex anatomical and visual conditions. We implement a hierarchical dynamic thresholding strategy to enhance sample assignment, and introduce an adaptive feature decoupling module based on deformable convolution to support dynamic spatial reconstruction. A cross layer dynamic weighting scheme further facilitates the fusion of semantic and detail features across multiple scales. Experimental results demonstrate that the model, with a size of only 5MB on both our PID dataset and Clinical datasets, achieves inference speeds of over 62 FPS on devices and 33 FPS on edge platforms, showing great potential in the application of emergency NTI.

Jinyu Liu, Gang Tan, Kiwan Maeng

Machine learning (ML) involves private data and proprietary model parameters. MPC-based ML allows multiple parties to collaboratively run an ML workload without sharing their private data or model parameters using multi-party computing (MPC). Because MPC cannot natively run ML operations such as Softmax or GELU, existing frameworks use different approximations. Our study shows that, on a well-optimized framework, these approximations often become the dominating bottleneck. Popular approximations are often insufficiently accurate or unnecessarily slow, and these issues are hard to identify and fix in existing frameworks. To tackle this issue, we propose a compiler for MPC-based ML, CrypTorch. CrypTorch disentangles these approximations with the rest of the MPC runtime, allows easily adding new approximations through its programming interface, and automatically selects approximations to maximize both performance and accuracy. Built as an extension to PyTorch 2's compiler, we show that CrypTorch's auto-tuning alone provides 1.20--1.7$\times$ immediate speedup without sacrificing accuracy, and 1.31--1.8$\times$ speedup when some accuracy degradation is allowed, compared to our well-optimized baseline. Combined with better engineering and adoption of state-of-the-art practices, the entire framework brings 3.22--8.6$\times$ end-to-end speedup compared to the popular framework, CrypTen.

Ziruo Yi, Jinyu Liu, Ting Xiao et al.

Radiology visual question answering (RVQA) provides precise answers to questions about chest X-ray images, alleviating radiologists' workload. While recent methods based on multimodal large language models (MLLMs) and retrieval-augmented generation (RAG) have shown promising progress in RVQA, they still face challenges in factual accuracy, hallucinations, and cross-modal misalignment. We introduce a multi-agent system (MAS) designed to support complex reasoning in RVQA, with specialized agents for context understanding, multimodal reasoning, and answer validation. We evaluate our system on a challenging RVQA set curated via model disagreement filtering, comprising consistently hard cases across multiple MLLMs. Extensive experiments demonstrate the superiority and effectiveness of our system over strong MLLM baselines, with a case study illustrating its reliability and interpretability. This work highlights the potential of multi-agent approaches to support explainable and trustworthy clinical AI applications that require complex reasoning.

Jinyu Liu, Xiaoying Song, Diana Zhang et al.

Providing subject access to information resources is an essential function of any library management system. Large language models (LLMs) have been widely used in classification and summarization tasks, but their capability to perform subject analysis is underexplored. Multi-label classification with traditional machine learning (ML) models has been used for subject analysis but struggles with unseen cases. LLMs offer an alternative but often over-generate and hallucinate. Therefore, we propose a hybrid framework that integrates embedding-based ML models with LLMs. This approach uses ML models to (1) predict the optimal number of LCSH labels to guide LLM predictions and (2) post-edit the predicted terms with actual LCSH terms to mitigate hallucinations. We experimented with LLMs and the hybrid framework to predict the subject terms of books using the Library of Congress Subject Headings (LCSH). Experiment results show that providing initial predictions to guide LLM generations and imposing post-edits result in more controlled and vocabulary-aligned outputs.

Mengjuan Liu, Jinyu Liu, Zhengning Hu et al.

Real-time bidding (RTB) has become a critical way of online advertising. In RTB, an advertiser can participate in bidding ad impressions to display its advertisements. The advertiser determines every impression's bidding price according to its bidding strategy. Therefore, a good bidding strategy can help advertisers improve cost efficiency. This paper focuses on optimizing a single advertiser's bidding strategy using reinforcement learning (RL) in RTB. Unfortunately, it is challenging to optimize the bidding strategy through RL at the granularity of impression due to the highly dynamic nature of the RTB environment. In this paper, we first utilize a widely accepted linear bidding function to compute every impression's base price and optimize it by a mutable adjustment factor derived from the RTB auction environment, to avoid optimizing every impression's bidding price directly. Specifically, we use the maximum entropy RL algorithm (Soft Actor-Critic) to optimize the adjustment factor generation policy at the impression-grained level. Finally, the empirical study on a public dataset demonstrates that the proposed bidding strategy has superior performance compared with the baselines.