Yunpeng Li

Wei Peng, Yue Hu, Luxi Xing et al.

Emotional support conversation aims at reducing the emotional distress of the help-seeker, which is a new and challenging task. It requires the system to explore the cause of help-seeker's emotional distress and understand their psychological intention to provide supportive responses. However, existing methods mainly focus on the sequential contextual information, ignoring the hierarchical relationships with the global cause and local psychological intention behind conversations, thus leads to a weak ability of emotional support. In this paper, we propose a Global-to-Local Hierarchical Graph Network to capture the multi-source information (global cause, local intentions and dialog history) and model hierarchical relationships between them, which consists of a multi-source encoder, a hierarchical graph reasoner, and a global-guide decoder. Furthermore, a novel training objective is designed to monitor semantic information of the global cause. Experimental results on the emotional support conversation dataset, ESConv, confirm that the proposed GLHG has achieved the state-of-the-art performance on the automatic and human evaluations. The code will be released in here \footnote{\small{~https://github.com/pengwei-iie/GLHG}}.

Wei Peng, Ziyuan Qin, Yue Hu et al.

Emotional Support Conversation (ESConv) aims to reduce help-seekers'emotional distress with the supportive strategy and response. It is essential for the supporter to select an appropriate strategy with the feedback of the help-seeker (e.g., emotion change during dialog turns, etc) in ESConv. However, previous methods mainly focus on the dialog history to select the strategy and ignore the help-seeker's feedback, leading to the wrong and user-irrelevant strategy prediction. In addition, these approaches only model the context-to-strategy flow and pay less attention to the strategy-to-context flow that can focus on the strategy-related context for generating the strategy-constrain response. In this paper, we propose a Feedback-Aware Double COntrolling Network (FADO) to make a strategy schedule and generate the supportive response. The core module in FADO consists of a dual-level feedback strategy selector and a double control reader. Specifically, the dual-level feedback strategy selector leverages the turn-level and conversation-level feedback to encourage or penalize strategies. The double control reader constructs the novel strategy-to-context flow for generating the strategy-constrain response. Furthermore, a strategy dictionary is designed to enrich the semantic information of the strategy and improve the quality of strategy-constrain response. Experimental results on ESConv show that the proposed FADO has achieved the state-of-the-art performance in terms of both strategy selection and response generation. Our code is available at https://github.com/Thedatababbler/FADO.

Ryan Banks, Bernat Rovira-Lastra, Jordi Martinez-Gomis et al.

Occlusal contacts are the locations at which the occluding surfaces of the maxilla and the mandible posterior teeth meet. Occlusal contact detection is a vital tool for restoring the loss of masticatory function and is a mandatory assessment in the field of dentistry, with particular importance in prosthodontics and restorative dentistry. The most common method for occlusal contact detection is articulating paper. However, this method can indicate significant medically false positive and medically false negative contact areas, leaving the identification of true occlusal indications to clinicians. To address this, we propose a multiclass Vision Transformer and Fully Convolutional Network ensemble semantic segmentation model with a combination hierarchical loss function, which we name as Hierarchical Fully Convolutional Branch Transformer (H-FCBFormer). We also propose a method of generating medically true positive semantic segmentation masks derived from expert annotated articulating paper masks and gold standard masks. The proposed model outperforms other machine learning methods evaluated at detecting medically true positive contacts and performs better than dentists in terms of accurately identifying object-wise occlusal contact areas while taking significantly less time to identify them. Code is available at https://github.com/Banksylel/H-FCBFormer.

Xiongjie Chen, Yunpeng Li, Yongxin Yang

Out-of-distribution (OOD) detection has recently received much attention from the machine learning community due to its importance in deploying machine learning models in real-world applications. In this paper we propose an uncertainty quantification approach by modelling the distribution of features. We further incorporate an efficient ensemble mechanism, namely batch-ensemble, to construct the batch-ensemble stochastic neural networks (BE-SNNs) and overcome the feature collapse problem. We compare the performance of the proposed BE-SNNs with the other state-of-the-art approaches and show that BE-SNNs yield superior performance on several OOD benchmarks, such as the Two-Moons dataset, the FashionMNIST vs MNIST dataset, FashionMNIST vs NotMNIST dataset, and the CIFAR10 vs SVHN dataset.

Yang Yang, Shao-Fu Shih, Hakan Erdogan et al.

High quality speech capture has been widely studied for both voice communication and human computer interface reasons. To improve the capture performance, we can often find multi-microphone speech enhancement techniques deployed on various devices. Multi-microphone speech enhancement problem is often decomposed into two decoupled steps: a beamformer that provides spatial filtering and a single-channel speech enhancement model that cleans up the beamformer output. In this work, we propose a speech enhancement solution that takes both the raw microphone and beamformer outputs as the input for an ML model. We devise a simple yet effective training scheme that allows the model to learn from the cues of the beamformer by contrasting the two inputs and greatly boost its capability in spatial rejection, while conducting the general tasks of denoising and dereverberation. The proposed solution takes advantage of classical spatial filtering algorithms instead of competing with them. By design, the beamformer module then could be selected separately and does not require a large amount of data to be optimized for a given form factor, and the network model can be considered as a standalone module which is highly transferable independently from the microphone array. We name the ML module in our solution as GSENet, short for Guided Speech Enhancement Network. We demonstrate its effectiveness on real world data collected on multi-microphone devices in terms of the suppression of noise and interfering speech.

Wenhan Li, Xiongjie Chen, Wenwu Wang et al.

Differentiable particle filters are an emerging class of particle filtering methods that use neural networks to construct and learn parametric state-space models. In real-world applications, both the state dynamics and measurements can switch between a set of candidate models. For instance, in target tracking, vehicles can idle, move through traffic, or cruise on motorways, and measurements are collected in different geographical or weather conditions. This paper proposes a new differentiable particle filter for regime-switching state-space models. The method can learn a set of unknown candidate dynamic and measurement models and track the state posteriors. We evaluate the performance of the novel algorithm in relevant models, showing its great performance compared to other competitive algorithms.

Zhi Qin Tan, Owen Addison, Yunpeng Li

High degrees of disagreement among annotators can exist for ambiguous objects, e.g. in medical images, underscoring the challenges of establishing ground truth annotations in object detection tasks. Despite this, all existing object detectors implicitly require access to ground truth annotations for either training or evaluation. The fundamental questions we target are: How can we learn an object detector with multiple annotators' annotations but without objective ground truth annotations due to object ambiguity, and how can we enable the learned detector to express meaningful model predictive uncertainties in detecting ambiguous objects? To answer these questions, we present an interpretable approach to calibrate probabilistic object detectors, where the calibration goal is to align the class confidence and bounding box variance estimates to the annotators' annotation distribution. We introduce an efficient yet effective framework to calibrate probabilistic object detectors by designing four evaluation metrics to measure calibration errors regarding classification and localization, and proposing a train-time calibration and post-hoc calibrator, all without the need to access any ground truth. This framework is generalizable to many existing probabilistic object detectors, such as the YOLO families and two-stage detectors. Empirical results with real-world and synthetic datasets of medical and natural images demonstrate the superior performance of the proposed framework with three popular object detectors.

Zhi Qin Tan, Olga Isupova, Gustavo Carneiro et al.

Acquiring fine-grained object detection annotations in unconstrained images is time-consuming, expensive, and prone to noise, especially in crowdsourcing scenarios. Most prior object detection methods assume accurate annotations; A few recent works have studied object detection with noisy crowdsourced annotations, with evaluation on distinct synthetic crowdsourced datasets of varying setups under artificial assumptions. To address these algorithmic limitations and evaluation inconsistency, we first propose a novel Bayesian Detector Combination (BDC) framework to more effectively train object detectors with noisy crowdsourced annotations, with the unique ability of automatically inferring the annotators' label qualities. Unlike previous approaches, BDC is model-agnostic, requires no prior knowledge of the annotators' skill level, and seamlessly integrates with existing object detection models. Due to the scarcity of real-world crowdsourced datasets, we introduce large synthetic datasets by simulating varying crowdsourcing scenarios. This allows consistent evaluation of different models at scale. Extensive experiments on both real and synthetic crowdsourced datasets show that BDC outperforms existing state-of-the-art methods, demonstrating its superiority in leveraging crowdsourced data for object detection. Our code and data are available at https://github.com/zhiqin1998/bdc.

Mingzhe Lu, Yiwen Wang, Yanbing Liu et al.

Computational narrative analysis aims to capture rhythm, tension, and emotional dynamics in literary texts. Existing large language models can generate long stories but overly focus on causal coherence, neglecting the complex story arcs and orchestration inherent in human narratives. This suggests a structural misalignment between model- and human-generated narratives. We therefore position narrative analysis as a diagnostic proxy for generation and propose VISTA Space, a high-dimensional framework for narrative orchestration that unifies human and model perspectives while jointly characterizing narrative function and structure in a common space. We further introduce LitVISTA, a structurally annotated benchmark grounded in literary texts, which operationalizes VISTA Space for systematic evaluation of models' narrative orchestration capabilities. Under an oracle setting with gold event anchors, we evaluate frontier LLMs including GPT, Claude, Grok, and Gemini. Results reveal systematic deficiencies, as current models struggle to jointly capture narrative function and structure and fail to form an integrated global view of literary narrative orchestration. End-to-end analysis further shows that failures are dominated by anchor identification and localization errors. Even advanced thinking modes yield mixed and often limited gains for literary narrative understanding.

Xiongjie Chen, Yunpeng Li

By approximating posterior distributions with weighted samples, particle filters (PFs) provide an efficient mechanism for solving non-linear sequential state estimation problems. While the effectiveness of particle filters has been recognised in various applications, their performance relies on the knowledge of dynamic models and measurement models, as well as the construction of effective proposal distributions. An emerging trend involves constructing components of particle filters using neural networks and optimising them by gradient descent, and such data-adaptive particle filtering approaches are often called differentiable particle filters. Due to the expressiveness of neural networks, differentiable particle filters are a promising computational tool for performing inference on sequential data in complex, high-dimensional tasks, such as vision-based robot localisation. In this paper, we review recent advances in differentiable particle filters and their applications. We place special emphasis on different design choices for key components of differentiable particle filters, including dynamic models, measurement models, proposal distributions, optimisation objectives, and differentiable resampling techniques.

John-Joseph Brady, Nikolas Nusken, Yunpeng Li

Latent state space systems are ubiquitous in statistical modelling, arising naturally when a time series is observed through a noisy measurement function, however training deep state space models (DSSM) at scale remains difficult. Two largely distinct strategies and literatures have developed around the training of DSSMs. Firstly, auto-encoding DSSMs train generative DSSMs by optimising a variational lower bound. Secondly, DSSMs trained by back-propagating the outputs of a classical sequential Monte Carlo algorithm (SMC). Such approaches can train DSSMs for discriminative as well as generative tasks, however, due to the sequentiality of their forward pass, scale poorly on modern hardware. We propose a new training method \emph{parallel variational Monte Carlo} (PVMC) that bridges the gap between the paradigms, and can be used robustly to train DSSMs for both discriminative and generative tasks. Our method achieves state-of-the-art or better results on a set of baseline experiments and trains $10\times$ faster than the fastest competing SMC approach.

Zhi Qin Tan, Xiatian Zhu, Owen Addison et al.

Diagnosing dental diseases from radiographs is time-consuming and challenging due to the subtle nature of diagnostic evidence. Existing methods, which rely on object detection models designed for natural images with more distinct target patterns, struggle to detect dental diseases that present with far less visual support. To address this challenge, we propose {\bf DentalX}, a novel context-aware dental disease detection approach that leverages oral structure information to mitigate the visual ambiguity inherent in radiographs. Specifically, we introduce a structural context extraction module that learns an auxiliary task: semantic segmentation of dental anatomy. The module extracts meaningful structural context and integrates it into the primary disease detection task to enhance the detection of subtle dental diseases. Extensive experiments on a dedicated benchmark demonstrate that DentalX significantly outperforms prior methods in both tasks. This mutual benefit arises naturally during model optimization, as the correlation between the two tasks is effectively captured. Our code is available at https://github.com/zhiqin1998/DentYOLOX.

Xiongjie Chen, Yunpeng Li

Tuning of measurement models is challenging in real-world applications of sequential Monte Carlo methods. Recent advances in differentiable particle filters have led to various efforts to learn measurement models through neural networks. But existing approaches in the differentiable particle filter framework do not admit valid probability densities in constructing measurement models, leading to incorrect quantification of the measurement uncertainty given state information. We propose to learn expressive and valid probability densities in measurement models through conditional normalizing flows, to capture the complex likelihood of measurements given states. We show that the proposed approach leads to improved estimation performance and faster training convergence in a visual tracking experiment.

Yuqiang Xie, Yue Hu, Yunpeng Li et al.

Controllable story generation is a challenging task in the field of NLP, which has attracted increasing research interest in recent years. However, most existing works generate a whole story conditioned on the appointed keywords or emotions, ignoring the psychological changes of the protagonist. Inspired by psychology theories, we introduce global psychological state chains, which include the needs and emotions of the protagonists, to help a story generation system create more controllable and well-planned stories. In this paper, we propose a Psychology-guIded Controllable Story Generation System (PICS) to generate stories that adhere to the given leading context and desired psychological state chains for the protagonist. Specifically, psychological state trackers are employed to memorize the protagonist's local psychological states to capture their inner temporal relationships. In addition, psychological state planners are adopted to gain the protagonist's global psychological states for story planning. Eventually, a psychology controller is designed to integrate the local and global psychological states into the story context representation for composing psychology-guided stories. Automatic and manual evaluations demonstrate that PICS outperforms baselines, and each part of PICS shows effectiveness for writing stories with more consistent psychological changes.

Vishal Thengane, Xiatian Zhu, Salim Bouzerdoum et al.

The 3D point cloud representation plays a crucial role in preserving the geometric fidelity of the physical world, enabling more accurate complex 3D environments. While humans naturally comprehend the intricate relationships between objects and variations through a multisensory system, artificial intelligence (AI) systems have yet to fully replicate this capacity. To bridge this gap, it becomes essential to incorporate multiple modalities. Models that can seamlessly integrate and reason across these modalities are known as foundation models (FMs). The development of FMs for 2D modalities, such as images and text, has seen significant progress, driven by the abundant availability of large-scale datasets. However, the 3D domain has lagged due to the scarcity of labelled data and high computational overheads. In response, recent research has begun to explore the potential of applying FMs to 3D tasks, overcoming these challenges by leveraging existing 2D knowledge. Additionally, language, with its capacity for abstract reasoning and description of the environment, offers a promising avenue for enhancing 3D understanding through large pre-trained language models (LLMs). Despite the rapid development and adoption of FMs for 3D vision tasks in recent years, there remains a gap in comprehensive and in-depth literature reviews. This article aims to address this gap by presenting a comprehensive overview of the state-of-the-art methods that utilize FMs for 3D visual understanding. We start by reviewing various strategies employed in the building of various 3D FMs. Then we categorize and summarize use of different FMs for tasks such as perception tasks. Finally, the article offers insights into future directions for research and development in this field. To help reader, we have curated list of relevant papers on the topic: https://github.com/vgthengane/Awesome-FMs-in-3D.

Yuanbo Hou, Vanja Zdravkovic, Marianne Sinka et al.

Mosquito-borne diseases affect more than one billion people each year and cause close to one million deaths. Traditional surveillance methods rely on traps and manual identification that are slow, labor-intensive, and difficult to scale. Audio-based mosquito monitoring offers a non-destructive, lower-cost, and more scalable complement to trap-based surveillance, but reliable species classification remains difficult under real-world recording conditions. Mosquito flight tones are narrow-band, often low in signal-to-noise ratio, and easily masked by background noise, and recordings for several epidemiologically relevant species remain limited, creating pronounced class imbalance. Variation across devices, environments, and collection protocols further increases the difficulty of robust classification. Such variation can cause models to rely on domain-specific recording artefacts rather than species-relevant acoustic cues, which makes transfer to new acquisition settings difficult. The BioDCASE 2026 Cross-Domain Mosquito Species Classification (CD-MSC) challenge is designed around this deployment problem by evaluating performance on both seen and unseen domains. This paper presents the official baseline system and evaluation pipeline as a simple, fully reproducible reference for the CD-MSC challenge task. The baseline uses log-mel features and a multitemporal resolution convolutional neural network (MTRCNN) with species and auxiliary domain outputs, together with complete training and test scripts. The baseline system performs strongly on seen domains but degrades markedly on unseen domains, showing that cross-domain generalisation, rather than within-domain recognition, is the central challenge for practical mosquito species classification from multi-source bioacoustic recordings.

Zhi Qin Tan, Xiatian Zhu, Owen Addison et al.

Cone-Beam Computed Tomography (CBCT) is a widely used 3D imaging technique in dentistry, providing volumetric information about the anatomical structures of jaws and teeth. Accurate segmentation of these anatomies is critical for clinical applications such as diagnosis and surgical planning, but remains time-consuming and challenging. In this paper, we present U-Mamba2, a new neural network architecture designed for multi-anatomy CBCT segmentation in the context of the ToothFairy3 challenge. U-Mamba2 integrates the Mamba2 state space models into the U-Net architecture, enforcing stronger structural constraints for higher efficiency without compromising performance. In addition, we integrate interactive click prompts with cross-attention blocks, pre-train U-Mamba2 using self-supervised learning, and incorporate dental domain knowledge into the model design to address key challenges of dental anatomy segmentation in CBCT. Extensive experiments, including independent tests, demonstrate that U-Mamba2 is both effective and efficient, securing first place in both tasks of the Toothfairy3 challenge. In Task 1, U-Mamba2 achieved a mean Dice of 0.84, HD95 of 38.17 with the held-out test data, with an average inference time of 40.58s. In Task 2, U-Mamba2 achieved the mean Dice of 0.87 and HD95 of 2.15 with the held-out test data. The code is publicly available at https://github.com/zhiqin1998/UMamba2.

Bo Wang, Wenbo Zhang, Yunpeng LI

The elaborate pavement performance prediction is an important premise of implementing preventive maintenance. Our survey reveals that in practice, the pavement performance is usually measured at segment-level, where an unique performance value is obtained for all lanes within one segment of 1km length. It still lacks more elaborate performance analysis at lane-level due to costly data collection and difficulty in prediction modeling. Therefore, this study developed a multi-task deep learning approach to predict the lane-level pavement performance with a large amount of historical segment-level performance measurement data. The unified prediction framework can effectively address inherent correlation and differences across lanes. In specific, the prediction framework firstly employed an Long Short-Term Memory (LSTM) layer to capture the segment-level pavement deterioration pattern. Then multiple task-specific LSTM layers were designed based on number of lanes to capture lane-level differences in pavement performance. Finally, we concatenated multiple task-specific LSTM outputs with auxiliary features for further training and obtained the lane-level predictions after fully connected layer. The aforementioned prediction framework was validated with a real case in China. It revealed a better model performance regardless of one-way 2-lane, 3-lane, and 4-lane scenarios, all lower than 10% in terms of mean absolute percentage error. The proposed prediction framework also outperforms other ensemble learning and shallow machine learning methods in almost every lane.

Zhi Qin Tan, Xiatian Zhu, Owen Addison et al.

Accurate segmentation of teeth and pulp in Cone-Beam Computed Tomography (CBCT) is vital for clinical applications like treatment planning and diagnosis. However, this process requires extensive expertise and is exceptionally time-consuming, highlighting the critical need for automated algorithms that can effectively utilize unlabeled data. In this paper, we propose U-Mamba2-SSL, a novel semi-supervised learning framework that builds on the U-Mamba2 model and employs a multi-stage training strategy. The framework first pre-trains U-Mamba2 in a self-supervised manner using a disruptive autoencoder. It then leverages unlabeled data through consistency regularization, where we introduce input and feature perturbations to ensure stable model outputs. Finally, a pseudo-labeling strategy is implemented with a reduced loss weighting to minimize the impact of potential errors. U-Mamba2-SSL achieved an average score of 0.789 and a DSC of 0.917 on the hidden test set, achieving first place in Task 1 of the STSR 2025 challenge. The code is available at https://github.com/zhiqin1998/UMamba2.

Junze Hu, Xiangyu Jin, Yizhe Zeng et al.

We introduce QLPro, a vulnerability detection framework that systematically integrates LLMs and static analysis tools to enable comprehensive vulnerability detection across entire open-source projects.We constructed a new dataset, JavaTest, comprising 10 open-source projects from GitHub with 62 confirmed vulnerabilities. CodeQL, a state-of-the-art static analysis tool, detected only 24 of these vulnerabilities while QLPro detected 41. Furthermore, QLPro discovered 6 previously unknown vulnerabilities, 2 of which have been confirmed as 0-days.

Georgios Papagiannis, Yunpeng Li

Imitation learning algorithms have been interpreted as variants of divergence minimization problems. The ability to compare occupancy measures between experts and learners is crucial in their effectiveness in learning from demonstrations. In this paper, we present tractable solutions by formulating imitation learning as minimization of the Sinkhorn distance between occupancy measures. The formulation combines the valuable properties of optimal transport metrics in comparing non-overlapping distributions with a cosine distance cost defined in an adversarially learned feature space. This leads to a highly discriminative critic network and optimal transport plan that subsequently guide imitation learning. We evaluate the proposed approach using both the reward metric and the Sinkhorn distance metric on a number of MuJoCo experiments. For the implementation and reproducing results please refer to the following repository https://github.com/gpapagiannis/sinkhorn-imitation.

Shaojie Zhuang, Lu Yin, Guangshun Wei et al.

Automatic tooth segmentation and identification from intra-oral scanned 3D models are fundamental problems in digital dentistry, yet most existing approaches rely on task-specific 3D neural networks trained with densely annotated datasets, resulting in high annotation cost and limited generalization to scans from unseen sources. Thus, we propose TSegAgent, which addresses these challenges by reformulating dental analysis as a zero-shot geometric reasoning problem rather than a purely data-driven recognition task. The key idea is to combine the representational capacity of general-purpose foundation models with explicit geometric inductive biases derived from dental anatomy. Instead of learning dental-specific features, the proposed framework leverages multi-view visual abstraction and geometry-grounded reasoning to infer tooth instances and identities without task-specific training. By explicitly encoding structural constraints such as dental arch organization and volumetric relationships, the method reduces uncertainty in ambiguous cases and mitigates overfitting to particular shape distributions. Experimental results demonstrate that this reasoning-oriented formulation enables accurate and reliable tooth segmentation and identification with low computational and annotation cost, while exhibiting strong generalization across diverse and previously unseen dental scans.

Mingzhe Lu, Yanbing Liu, Qihao Wang et al.

Movie scripts pose a fundamental challenge for automatic summarization due to their non-linear, cross-cut narrative structure, which makes surface-level saliency methods ineffective at preserving core story progression. To address this, we introduce S^2tory (Story Spine Distillation), a narratology-grounded framework that leverages character development trajectories to identify plot nuclei, the essential events that drive the narrative forward, while filtering out peripheral satellite events that merely enrich atmosphere or emotion. Our Narrative Expert Agent (NEAgent) performs theory-constrained reasoning, whose distilled knowledge conditions a small model to identify plot nuclei. Another model then uses these plot nuclei to generate the summary. Experiments on the MovieSum dataset demonstrate state-of-the-art semantic fidelity at approximately 3.5x compression, and zero-shot evaluation on BookSum confirms strong out-of-domain generalization. Human evaluation further validates that narratological theory provides an indispensable foundation for modeling complex, non-linear narratives.

Yang Yang, Yury Kartynnik, Yunpeng Li et al.

We present StreamVC, a streaming voice conversion solution that preserves the content and prosody of any source speech while matching the voice timbre from any target speech. Unlike previous approaches, StreamVC produces the resulting waveform at low latency from the input signal even on a mobile platform, making it applicable to real-time communication scenarios like calls and video conferencing, and addressing use cases such as voice anonymization in these scenarios. Our design leverages the architecture and training strategy of the SoundStream neural audio codec for lightweight high-quality speech synthesis. We demonstrate the feasibility of learning soft speech units causally, as well as the effectiveness of supplying whitened fundamental frequency information to improve pitch stability without leaking the source timbre information.

Xiongjie Chen, Yunpeng Li

Recently, there has been a surge of interest in incorporating neural networks into particle filters, e.g. differentiable particle filters, to perform joint sequential state estimation and model learning for non-linear non-Gaussian state-space models in complex environments. Existing differentiable particle filters are mostly constructed with vanilla neural networks that do not allow density estimation. As a result, they are either restricted to a bootstrap particle filtering framework or employ predefined distribution families (e.g. Gaussian distributions), limiting their performance in more complex real-world scenarios. In this paper we present a differentiable particle filtering framework that uses (conditional) normalizing flows to build its dynamic model, proposal distribution, and measurement model. This not only enables valid probability densities but also allows the proposed method to adaptively learn these modules in a flexible way, without being restricted to predefined distribution families. We derive the theoretical properties of the proposed filters and evaluate the proposed normalizing flow-based differentiable particle filters' performance through a series of numerical experiments.

Ryan Banks, Camila Lindoni Azevedo, Hongying Tang et al.

Accurate understanding of anatomical structures is essential for reliably staging certain dental diseases. A way of introducing this within semantic segmentation models is by utilising hierarchy-aware methodologies. However, existing hierarchy-aware segmentation methods largely encode anatomical structure through the loss functions, providing weak and indirect supervision. We introduce a general framework that embeds an explicit anatomical hierarchy into semantic segmentation by coupling a recurrent, level-wise prediction scheme with restrictive output heads and top-down feature conditioning. At each depth of the class tree, the backbone is re-run on the original image concatenated with logits from the previous level. Child class features are conditioned using Feature-wise Linear Modulation of their parent class probabilities, to modulate child feature spaces for fine grained detection. A probabilistic composition rule enforces consistency between parent and descendant classes. Hierarchical loss combines per-level class weighted Dice and cross entropy loss and a consistency term loss, ensuring parent predictions are the sum of their children. We validate our approach on our proposed dataset, TL-pano, containing 194 panoramic radiographs with dense instance and semantic segmentation annotations, of tooth layers and alveolar bone. Utilising UNet and HRNet as donor models across a 5-fold cross validation scheme, the hierarchical variants consistently increase IoU, Dice, and recall, particularly for fine-grained anatomies, and produce more anatomically coherent masks. However, hierarchical variants also demonstrated increased recall over precision, implying increased false positives. The results demonstrate that explicit hierarchical structuring improves both performance and clinical plausibility, especially in low data dental imaging regimes.

Yunpeng Li, Kehang Han, Brian McWilliams et al.

We propose SpectroStream, a full-band multi-channel neural audio codec. Successor to the well-established SoundStream, SpectroStream extends its capability beyond 24 kHz monophonic audio and enables high-quality reconstruction of 48 kHz stereo music at bit rates of 4--16 kbps. This is accomplished with a new neural architecture that leverages audio representation in the time-frequency domain, which leads to better audio quality especially at higher sample rate. The model also uses a delayed-fusion strategy to handle multi-channel audio, which is crucial in balancing per-channel acoustic quality and cross-channel phase consistency.

Lyria Team, Antoine Caillon, Brian McWilliams et al.

We introduce a new class of generative models for music called live music models that produce a continuous stream of music in real-time with synchronized user control. We release Magenta RealTime, an open-weights live music model that can be steered using text or audio prompts to control acoustic style. On automatic metrics of music quality, Magenta RealTime outperforms other open-weights music generation models, despite using fewer parameters and offering first-of-its-kind live generation capabilities. We also release Lyria RealTime, an API-based model with extended controls, offering access to our most powerful model with wide prompt coverage. These models demonstrate a new paradigm for AI-assisted music creation that emphasizes human-in-the-loop interaction for live music performance.

Adarsh Kappiyath, Abhra Chaudhuri, Ajay Jaiswal et al.

Ranking samples by fine-grained estimates of spuriosity (the degree to which spurious cues are present) has recently been shown to significantly benefit bias mitigation, over the traditional binary biased-\textit{vs}-unbiased partitioning of train sets. However, this spuriosity ranking comes with the requirement of human supervision. In this paper, we propose a debiasing framework based on our novel \ul{Se}lf-Guided \ul{B}ias \ul{Ra}nking (\emph{Sebra}), that mitigates biases (spurious correlations) via an automatic ranking of data points by spuriosity within their respective classes. Sebra leverages a key local symmetry in Empirical Risk Minimization (ERM) training -- the ease of learning a sample via ERM inversely correlates with its spuriousity; the fewer spurious correlations a sample exhibits, the harder it is to learn, and vice versa. However, globally across iterations, ERM tends to deviate from this symmetry. Sebra dynamically steers ERM to correct this deviation, facilitating the sequential learning of attributes in increasing order of difficulty, \ie, decreasing order of spuriosity. As a result, the sequence in which Sebra learns samples naturally provides spuriousity rankings. We use the resulting fine-grained bias characterization in a contrastive learning framework to mitigate biases from multiple sources. Extensive experiments show that Sebra consistently outperforms previous state-of-the-art unsupervised debiasing techniques across multiple standard benchmarks, including UrbanCars, BAR, CelebA, and ImageNet-1K. Code, pre-trained models, and training logs are available at https://kadarsh22.github.io/sebra_iclr25/.

John-Joseph Brady, Yuhui Luo, Wenwu Wang et al.

Differentiable particle filters are an emerging class of models that combine sequential Monte Carlo techniques with the flexibility of neural networks to perform state space inference. This paper concerns the case where the system may switch between a finite set of state-space models, i.e. regimes. No prior approaches effectively learn both the individual regimes and the switching process simultaneously. In this paper, we propose the neural network based regime learning differentiable particle filter (RLPF) to address this problem. We further design a training procedure for the RLPF and other related algorithms. We demonstrate competitive performance compared to the previous state-of-the-art algorithms on a pair of numerical experiments.

Jiaxi Li, John-Joseph Brady, Xiongjie Chen et al.

Differentiable particle filters combine the flexibility of neural networks with the probabilistic nature of sequential Monte Carlo methods. However, traditional approaches rely on the availability of labelled data, i.e., the ground truth latent state information, which is often difficult to obtain in real-world applications. This paper compares the effectiveness of two semi-supervised training objectives for differentiable particle filters. We present results in two simulated environments where labelled data are scarce.

Yizhe Zeng, Wei Zhang, Yunpeng Li et al.

While Chain-of-Thought (CoT) prompting has become a standard paradigm for eliciting complex reasoning capabilities in Large Language Models, it inadvertently exposes a new attack surface for backdoor attacks. Existing CoT backdoor attacks typically manipulate the intermediate reasoning steps to steer the model toward incorrect answers. However, these corrupted reasoning traces are readily detected by prevalent process-monitoring defenses. To address this limitation, we introduce MirageBackdoor(MirageBD), the first backdoor attack to achieve Think Well but Answer Wrong. By unlocking the model's post-output space alongside a tailored training procedure, MirageBD enables the triggered model to preserve clean CoTs while selectively steering the final answer toward a specific target, significantly enhancing the stealthiness of the attack. Experiments show that MirageBD generally achieves over 90% attack success rate across four datasets and five models with a poison ratio of only 5%. Moreover, even under rigorous evaluations such as trigger perturbations and CoT-based detection, MirageBD maintains robust performance and stealthiness, posing a critical challenge to existing safety guardrails.

John-Joseph Brady, Benjamin Cox, Yunpeng Li et al.

State-space models (SSMs) are a widely used tool in time series analysis. In the complex systems that arise from real-world data, it is common to employ particle filtering (PF), an efficient Monte Carlo method for estimating the hidden state corresponding to a sequence of observations. Applying particle filtering requires specifying both the parametric form and the parameters of the system, which are often unknown and must be estimated. Gradient-based optimisation techniques cannot be applied directly to standard particle filters, as the filters themselves are not differentiable. However, several recently proposed methods modify the resampling step to make particle filtering differentiable. In this paper, we present an implementation of several such differentiable particle filters (DPFs) with a unified API built on the popular PyTorch framework. Our implementation makes these algorithms easily accessible to a broader research community and facilitates straightforward comparison between them. We validate our framework by reproducing experiments from several existing studies and demonstrate how DPFs can be applied to address several common challenges with state space modelling.

Wei Zhang, Juan Chen, En Zhu et al.

Automated depression diagnosis aims to analyze multimodal information from interview videos to predict participants' depression scores. Previous studies often lack clear explanations of how these scores were determined, limiting their adoption in clinical practice. While the advent of LLMs provides a possible pathway for explainable depression diagnosis, current LLMs capable of processing multimodal data lack training on interview data, resulting in poor diagnostic performance when used directly. In this paper, we propose a novel multimodal large language model (MLlm-DR) that can understand multimodal information inputs and supports explainable depression diagnosis. MLlm-DR integrates a smaller LLMs and a lightweight query module (LQ-former). Specifically, the smaller LLMs is designed to generate depression scores and corresponding evaluation rationales. To enhance its logical reasoning for domain-specific tasks while maintaining practicality, we constructed a robust training dataset to fine-tune it. Meanwhile, the LQ-former captures depression-related features from speech and visual data, aiding the model's ability to process multimodal information, to achieve comprehensive depression diagnosis. Our approach achieves state-of-the-art results on two interview-based benchmark datasets, CMDC and E-DAIC-WOZ, demonstrating its effectiveness and superiority.

Yang Yang, Yunpeng Li, George Sung et al.

Token-based language modeling is a prominent approach for speech generation, where tokens are obtained by quantizing features from self-supervised learning (SSL) models and extracting codes from neural speech codecs, generally referred to as semantic tokens and acoustic tokens. These tokens are often modeled autoregressively, with the inference speed being constrained by the token rate. In this work, we propose DiffSoundStream, a solution that improves the efficiency of speech tokenization in non-streaming scenarios through two techniques: (1) conditioning the neural codec on semantic tokens to minimize redundancy between semantic and acoustic tokens, and (2) leveraging latent diffusion models to synthesize high-quality waveforms from semantic and coarse-level acoustic tokens. Experiments show that at 50 tokens per second, DiffSoundStream achieves speech quality on par with a standard SoundStream model operating at twice the token rate. Additionally, we achieve step-size distillation using just four diffusion sampling steps with only a minor quality loss.

Ryan Banks, Vishal Thengane, María Eugenia Guerrero et al.

This study proposes a deep learning framework and annotation methodology for the automatic detection of periodontal bone loss landmarks, associated conditions, and staging. 192 periapical radiographs were collected and annotated with a stage agnostic methodology, labelling clinically relevant landmarks regardless of disease presence or extent. We propose a heuristic post-processing module that aligns predicted keypoints to tooth boundaries using an auxiliary instance segmentation model. An evaluation metric, Percentage of Relative Correct Keypoints (PRCK), is proposed to capture keypoint performance in dental imaging domains. Four donor pose estimation models were adapted with fine-tuning for our keypoint problem. Post-processing improved fine-grained localisation, raising average PRCK^{0.05} by +0.028, but reduced coarse performance for PRCK^{0.25} by -0.0523 and PRCK^{0.5} by -0.0345. Orientation estimation shows excellent performance for auxiliary segmentation when filtered with either stage 1 object detection model. Periodontal staging was detected sufficiently, with the best mesial and distal Dice scores of 0.508 and 0.489, while furcation involvement and widened periodontal ligament space tasks remained challenging due to scarce positive samples. Scalability is implied with similar validation and external set performance. The annotation methodology enables stage agnostic training with balanced representation across disease severities for some detection tasks. The PRCK metric provides a domain-specific alternative to generic pose metrics, while the heuristic post-processing module consistently corrected implausible predictions with occasional catastrophic failures. The proposed framework demonstrates the feasibility of clinically interpretable periodontal bone loss assessment, with potential to reduce diagnostic variability and clinician workload.

Jiaxi Li, Xiongjie Chen, Yunpeng Li

Differentiable particle filters are an emerging class of sequential Bayesian inference techniques that use neural networks to construct components in state space models. Existing approaches are mostly based on offline supervised training strategies. This leads to the delay of the model deployment and the obtained filters are susceptible to distribution shift of test-time data. In this paper, we propose an online learning framework for differentiable particle filters so that model parameters can be updated as data arrive. The technical constraint is that there is no known ground truth state information in the online inference setting. We address this by adopting an unsupervised loss to construct the online model updating procedure, which involves a sequence of filtering operations for online maximum likelihood-based parameter estimation. We empirically evaluate the effectiveness of the proposed method, and compare it with supervised learning methods in simulation settings including a multivariate linear Gaussian state-space model and a simulated object tracking experiment.

Yuqiang Xie, Yue Hu, Luxi Xing et al.

Story Ending Generation (SEG) is a challenging task in natural language generation. Recently, methods based on Pre-trained Language Models (PLM) have achieved great prosperity, which can produce fluent and coherent story endings. However, the pre-training objective of PLM-based methods is unable to model the consistency between story context and ending. The goal of this paper is to adopt contrastive learning to generate endings more consistent with story context, while there are two main challenges in contrastive learning of SEG. First is the negative sampling of wrong endings inconsistent with story contexts. The second challenge is the adaptation of contrastive learning for SEG. To address these two issues, we propose a novel Contrastive Learning framework for Story Ending Generation (CLSEG), which has two steps: multi-aspect sampling and story-specific contrastive learning. Particularly, for the first issue, we utilize novel multi-aspect sampling mechanisms to obtain wrong endings considering the consistency of order, causality, and sentiment. To solve the second issue, we well-design a story-specific contrastive training strategy that is adapted for SEG. Experiments show that CLSEG outperforms baselines and can produce story endings with stronger consistency and rationality.

Yunpeng Li, ZhaoHui Ye

Independent component analysis is intended to recover the mutually independent components from their linear mixtures. This technique has been widely used in many fields, such as data analysis, signal processing, and machine learning. To alleviate the dependency on prior knowledge concerning unknown sources, many nonparametric methods have been proposed. In this paper, we present a novel boosting-based algorithm for independent component analysis. Our algorithm consists of maximizing likelihood estimation via boosting and seeking unmixing matrix by the fixed-point method. A variety of experiments validate its performance compared with many of the presently known algorithms.

YunPeng Li

Independent Component Analysis (ICA) is intended to recover the mutually independent sources from their linear mixtures, and F astICA is one of the most successful ICA algorithms. Although it seems reasonable to improve the performance of F astICA by introducing more nonlinear functions to the negentropy estimation, the original fixed-point method (approximate Newton method) in F astICA degenerates under this circumstance. To alleviate this problem, we propose a novel method based on the second-order approximation of minimum discrimination information (MDI). The joint maximization in our method is consisted of minimizing single weighted least squares and seeking unmixing matrix by the fixed-point method. Experimental results validate its efficiency compared with other popular ICA algorithms.

Ivan Kiskin, Marianne Sinka, Adam D. Cobb et al.

This paper presents the first large-scale multi-species dataset of acoustic recordings of mosquitoes tracked continuously in free flight. We present 20 hours of audio recordings that we have expertly labelled and tagged precisely in time. Significantly, 18 hours of recordings contain annotations from 36 different species. Mosquitoes are well-known carriers of diseases such as malaria, dengue and yellow fever. Collecting this dataset is motivated by the need to assist applications which utilise mosquito acoustics to conduct surveys to help predict outbreaks and inform intervention policy. The task of detecting mosquitoes from the sound of their wingbeats is challenging due to the difficulty in collecting recordings from realistic scenarios. To address this, as part of the HumBug project, we conducted global experiments to record mosquitoes ranging from those bred in culture cages to mosquitoes captured in the wild. Consequently, the audio recordings vary in signal-to-noise ratio and contain a broad range of indoor and outdoor background environments from Tanzania, Thailand, Kenya, the USA and the UK. In this paper we describe in detail how we collected, labelled and curated the data. The data is provided from a PostgreSQL database, which contains important metadata such as the capture method, age, feeding status and gender of the mosquitoes. Additionally, we provide code to extract features and train Bayesian convolutional neural networks for two key tasks: the identification of mosquitoes from their corresponding background environments, and the classification of detected mosquitoes into species. Our extensive dataset is both challenging to machine learning researchers focusing on acoustic identification, and critical to entomologists, geo-spatial modellers and other domain experts to understand mosquito behaviour, model their distribution, and manage the threat they pose to humans.

YunPeng Li

Convolutive blind source separation (BSS) is intended to recover the unknown components from their convolutive mixtures. Contrary to the contrast functions used in instantaneous cases, the spatial-temporal prewhitening stage and the para-unitary filters constraint are difficult to implement in a convolutive context. In this paper, we propose several modifications of FastICA to alleviate these difficulties. Our method performs the simple prewhitening step on convolutive mixtures prior to the separation and optimizes the contrast function under the diagonalization constraint implemented by single value decomposition (SVD). Numerical simulations are implemented to verify the performance of the proposed method.

Xiongjie Chen, Hao Wen, Yunpeng Li

Differentiable particle filters provide a flexible mechanism to adaptively train dynamic and measurement models by learning from observed data. However, most existing differentiable particle filters are within the bootstrap particle filtering framework and fail to incorporate the information from latest observations to construct better proposals. In this paper, we utilize conditional normalizing flows to construct proposal distributions for differentiable particle filters, enriching the distribution families that the proposal distributions can represent. In addition, normalizing flows are incorporated in the construction of the dynamic model, resulting in a more expressive dynamic model. We demonstrate the performance of the proposed conditional normalizing flow-based differentiable particle filters in a visual tracking task.

Conghui Hu, Yongxin Yang, Yunpeng Li et al.

The practical value of existing supervised sketch-based image retrieval (SBIR) algorithms is largely limited by the requirement for intensive data collection and labeling. In this paper, we present the first attempt at unsupervised SBIR to remove the labeling cost (both category annotations and sketch-photo pairings) that is conventionally needed for training. Existing single-domain unsupervised representation learning methods perform poorly in this application, due to the unique cross-domain (sketch and photo) nature of the problem. We therefore introduce a novel framework that simultaneously performs sketch-photo domain alignment and semantic-aware representation learning. Technically this is underpinned by introducing joint distribution optimal transport (JDOT) to align data from different domains, which we extend with trainable cluster prototypes and feature memory banks to further improve scalability and efficacy. Extensive experiments show that our framework achieves excellent performance in the new unsupervised setting, and performs comparably or better than state-of-the-art in the zero-shot setting.

YunPeng Li, ZhaoHui Ye

Nonparametric maximum likelihood estimation is intended to infer the unknown density distribution while making as few assumptions as possible. To alleviate the over parameterization in nonparametric data fitting, smoothing assumptions are usually merged into the estimation. In this paper a novel boosting-based method is introduced to the nonparametric estimation in univariate cases. We deduce the boosting algorithm by the second-order approximation of nonparametric log-likelihood. Gaussian kernel and smooth spline are chosen as weak learners in boosting to satisfy the smoothing assumptions. Simulations and real data experiments demonstrate the efficacy of the proposed approach.

Hao Wen, Xiongjie Chen, Georgios Papagiannis et al.

Recent advances in incorporating neural networks into particle filters provide the desired flexibility to apply particle filters in large-scale real-world applications. The dynamic and measurement models in this framework are learnable through the differentiable implementation of particle filters. Past efforts in optimising such models often require the knowledge of true states which can be expensive to obtain or even unavailable in practice. In this paper, in order to reduce the demand for annotated data, we present an end-to-end learning objective based upon the maximisation of a pseudo-likelihood function which can improve the estimation of states when large portion of true states are unknown. We assess performance of the proposed method in state estimation tasks in robotics with simulated and real-world datasets.

Yunpeng Li, Marco Tagliasacchi, Oleg Rybakov et al.

In this paper we propose a lightweight model for frequency bandwidth extension of speech signals, increasing the sampling frequency from 8kHz to 16kHz while restoring the high frequency content to a level almost indistinguishable from the 16kHz ground truth. The model architecture is based on SEANet (Sound EnhAncement Network), a wave-to-wave fully convolutional model, which uses a combination of feature losses and adversarial losses to reconstruct an enhanced version of the input speech. In addition, we propose a variant of SEANet that can be deployed on-device in streaming mode, achieving an architectural latency of 16ms. When profiled on a single core of a mobile CPU, processing one 16ms frame takes only 1.5ms. The low latency makes it viable for bi-directional voice communication systems.

Zalán Borsos, Yunpeng Li, Beat Gfeller et al.

A crucial aspect for the successful deployment of audio-based models "in-the-wild" is the robustness to the transformations introduced by heterogeneous acquisition conditions. In this work, we propose a method to perform one-shot microphone style transfer. Given only a few seconds of audio recorded by a target device, MicAugment identifies the transformations associated to the input acquisition pipeline and uses the learned transformations to synthesize audio as if it were recorded under the same conditions as the target audio. We show that our method can successfully apply the style transfer to real audio and that it significantly increases model robustness when used as data augmentation in the downstream tasks.

Marco Tagliasacchi, Yunpeng Li, Karolis Misiunas et al.

We explore the possibility of leveraging accelerometer data to perform speech enhancement in very noisy conditions. Although it is possible to only partially reconstruct user's speech from the accelerometer, the latter provides a strong conditioning signal that is not influenced from noise sources in the environment. Based on this observation, we feed a multi-modal input to SEANet (Sound EnhAncement Network), a wave-to-wave fully convolutional model, which adopts a combination of feature losses and adversarial losses to reconstruct an enhanced version of user's speech. We trained our model with data collected by sensors mounted on an earbud and synthetically corrupted by adding different kinds of noise sources to the audio signal. Our experimental results demonstrate that it is possible to achieve very high quality results, even in the case of interfering speech at the same level of loudness. A sample of the output produced by our model is available at https://google-research.github.io/seanet/multimodal/speech.

Yunpeng Li, Beat Gfeller, Marco Tagliasacchi et al.

We propose an audio-to-audio neural network model that learns to denoise old music recordings. Our model internally converts its input into a time-frequency representation by means of a short-time Fourier transform (STFT), and processes the resulting complex spectrogram using a convolutional neural network. The network is trained with both reconstruction and adversarial objectives on a synthetic noisy music dataset, which is created by mixing clean music with real noise samples extracted from quiet segments of old recordings. We evaluate our method quantitatively on held-out test examples of the synthetic dataset, and qualitatively by human rating on samples of actual historical recordings. Our results show that the proposed method is effective in removing noise, while preserving the quality and details of the original music.