205 accepted papers
Point clouds provide a compact and expressive representation of 3D objects, and have recently been integrated into multimodal large language models (MLLMs). However, existing methods primarily focus on static objects, while understanding dynamic point cloud sequences remains largely unexplored. This…
Over-smoothing (OSM) and over-squashing (OSQ) are two fundamental phenomena that limit the performance of Graph Neural Networks (GNNs), yet a unified spectral-spatial understanding of these phenomena remains underexplored. In this paper, we adopt polynomial spectral filters as an analytical tool to
Most existing Graph Neural Networks (GNNs) rely on the node-level message passing or attention mechanisms to propagate and extract useful information. Although recent advances attempt to move beyond purely the node-level propagation by constructing high-level representations, these approaches are of
Whisper speech recognition is crucial not only for ensuring privacy in sensitive communications but also for providing a critical communication bridge for patients under vocal restraint and enabling discrete interaction in noise-sensitive environments. The development of Chinese mandarin audio-visua…
Large Language Models (LLMs) have demonstrated impressive capabilities in code generation. Like human programmers, LLMs tend to call high-level APIs and libraries to program efficiently. However, this shortcut may hinder LLMs from learning the essential algorithm reasoning, leading instead to rote m
Positive-unlabeled (PU) learning is a weakly supervised binary classification problem, in which the goal is to learn a binary classifier from only positive and unlabeled data, without access to negative data. In recent years, many PU learning algorithms have been developed to improve model performan…
The rapid development of image manipulation technologies poses significant challenges to multimedia forensics, especially in accurate localization of manipulated regions. Existing methods often fail to fully explore the intrinsic discrepancies between manipulated and authentic regions, resulting in
Visual anomaly detection is limited by the lack of sufficient anomaly data. While existing anomaly synthesis methods have made remarkable progress, achieving both realism and diversity in synthesis remains a major obstacle. To address this, we propose AnomalyPainter, a novel framework that breaks th
Cooperative perception (CP) enhances situational awareness of connected and autonomous vehicles by exchanging and combining messages from multiple agents. While prior work has explored adversarial integrity attacks that degrade detection accuracy, little is known about CP
Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples. Yet most pipelines treat SGG as a one-shot, deterministic classification instead of a genuine progressive, generative task. We propose FlowSG, which re
Component-level audio Spoofing (Comp-Spoof) targets a new form of audio manipulation where only specific components of a signal, such as speech or environmental sound, are forged or substituted while other components remain genuine. Existing anti-spoofing datasets and methods treat an utterance or a…
Transformer architectures have dramatically advanced representation learning and inference in deep models through self-attention mechanisms. In parallel, associative memory (AM) frameworks map representations onto energy landscapes, offering interpretable retrieval mechanisms. However, their continu…
Improving LLM performance on downstream tasks sometimes requires leveraging auxiliary datasets during post-training. In practice, however, developers face constraints on compute, labeling, and licensing costs that preclude using all available data, necessitating principled dataset-level selection. T…
Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding. Despite their success, LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content. To address this issu
Despite the remarkable progress of 3D generation, achieving controllability, i.e., ensuring consistency between generated 3D content and input conditions like edge and depth, remains a significant challenge. Existing methods often struggle to maintain accurate alignment, leading to noticeable discre
Cooperative localization is essential for swarm applications like collaborative exploration and search-and-rescue missions. However, maintaining real-time capability, robustness, and computational efficiency on resource-constrained platforms presents significant challenges. To address these challeng…
Large-scale video repositories are increasingly available for modern video understanding and generation tasks. However, transforming raw videos into high-quality, task-specific datasets remains costly and inefficient. We present DataCube, an intelligent platform for automatic video processing, multi
We present a novel dual-end complementary method for online depth estimation and mesh reconstruction, termed DepthMesh. Unlike most existing state-of-the-art methods that produce either only depth online or surface mesh offline, our method tightly couples online multiview depth estimation and Trunca…
Large language models (LLMs) show significant improvement in code generation. A common practice is sampling multiple candidate codes to increase the likelihood of producing an accurate solution. However, effectively identifying the best candidate from the pool is a significant challenge. Although ex
Pre-trained foundation models have demonstrated remarkable success in audio, vision and language, yet their potential for general machine signal modeling with arbitrary sampling rates-covering acoustic, vibration, and other industrial sensor data-remains under-explored. In this work, we propose a no…
Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, current event-based MLLMs often rely on dense image-like processing paradigms, overlooking the spatiotemporal sparsity of eve…
Theory of Mind (ToM) is a must-acquire skill for modern foundation model systems to operate effectively and safely in the real world. Recent works have explored honing ToM via post-training; however, we show that such progress is confounded by a pervasive “shortcut” issue: tasks can reach up to 99% …
Graph Convolutional Networks (GCNs) are defined based on aggregating the node information of adjacent nodes, that are usually treated as equally important as each other, limiting the representational power of existing GCNs for graph classification. To address this shortcoming, we propose a novel Glo…
In recent years, hypergraph contrastive learning methods have gained widespread attention due to their excellent performance in processing high-order structural data. However, traditional hypergraph learning method often assume that neighboring nodes are homogeneous, which can lead to the mixing of …
Human motion in human-robot interaction (HRI) is inherently uncertain, even when performing the same task repeatedly. This variability poses a significant challenge for prediction, as models must capture a distribution of plausible futures rather than a single deterministic trajectory. Traditional g…
LLM Ensemble---which involves the comprehensive use of multiple large language models (LLMs), each aimed at handling user queries during downstream inference, to benefit from their individual strengths---has gained substantial attention recently. The widespread availability of LLMs, coupled with the
Hypergraph neural networks (HNNs) have emerged as powerful tools for modeling high-order relationships in complex systems. However, most existing HNNs are designed under the assumption of homophily, which does not hold in many real-world scenarios where connected nodes often exhibit diverse semantic
Hypergraph neural networks (HGNNs) have shown great potential in modeling higher-order relationships among multiple entities. However, most existing HGNNs primarily emphasize low-pass filtering while neglecting the role of high-frequency information. In this work, we present a theoretical investigat
Unsupervised hypergraph representation learning has recently gained traction for its ability to model complex high-order interactions without requiring labeled data. However, existing contrastive learning methods typically overlook the frequency diversity inherent in hypergraph signals. To address t
Out-of-distribution (OOD) detection plays a critical role in ensuring the robustness of machine learning models in open-world settings. While extensive efforts have been made in vision, language, and graph domains, the challenge of OOD detection in hypergraph-structured data remains unexplored. In t
In recent years, the gait parsing sequence has become increasingly popular due to its higher information entropy than the binary silhouette and the keypoint-based skeleton. However, existing parsing-based gait recognition methods have not fully explored the complex, non-linear relationships between
Hyperedge prediction plays a critical role in high-order relational modeling with hypergraphs, yet most existing methods primarily focus on sampling strategies or local aggregation within candidate hyperedges. These approaches often overlook global structural dependencies that are essential for lear
The learnware paradigm aims to establish a market of learnwares, each of which is a well-trained model combined with a specification that describes its functionality without leaking data privacy. The market enables users to efficiently reuse relevant models based on specifications on their own tasks…
Decoding visual representations from brain signals has attracted significant attention in both neuroscience and artificial intelligence. However, the degree to which brain signals truly encode visual information remains unclear. Current visual decoding approaches explore various brain–image alignmen…
Human visual preferences are inherently multi-dimensional, encompassing aspects of aesthetics, detail fidelity, and semantic alignment. However, existing open-source preference datasets provide only single, holistic annotations, resulting in severe label noise—images that excel in some dimensions (e…
Current research on video hallucination mitigation primarily focuses on isolated error types, leaving *compositional* hallucinations—arising from incorrect reasoning over multiple interacting spatial and temporal factors largely underexplored. We introduce **OmniVCHall**, a benchmark designed to sys…
Recent research in long-form video generation has shifted from bidirectional to autoregressive models, yet these methods commonly suffer from error accumulation and a loss of long-term coherence. While attention sink frames have been introduced to mitigate this performance decay, they often induce a
Molecular property prediction from 3D structures is fundamentally constrained by the scarcity of labeled data. To address this challenge, researchers have adapted various self-supervised pre-training methods from computer vision and natural language processing; however, these approaches often neglec…
Dataset distillation (DD) compresses a large training set into a small synthetic set for efficient training, but most DD methods optimize only clean accuracy and leave robustness uncontrolled. Recent robust DD methods improve robustness, yet they often suffer from a poor accuracy–robustness trade-of…
Existing solutions for bundle recommendation (BR) have achieved remarkable effectiveness for predicting the user’s preference for prebuilt bundles. However, bundle-item (B-I) affiliation will vary dynamically in real scenarios. For ex ample, a bundle themed as ‘casual outfit’ may add ‘hat’ or re
Large multimodal models (LMMs) are increasingly adopted as judges in multimodal evaluation systems due to their strong instruction following and consistency with human preferences. However, their ability to follow diverse, fine-grained evaluation criteria remains underexplored. We develop Multi-Crit
Session-based recommendation aims to predict users’ next actions by modeling their ongoing interaction sequences, particularly in scenarios where long-term user profiles are unavailable. While existing methods have achieved promising results by leveraging sequential and graph-based structures, they
Existing industrial 3D garment meshes already cover most real-world clothing geometries, yet their texture diversity remains limited. To acquire more realistic textures, generative methods are often used to extract Physically-based Rendering (PBR) textures and materials from large collections of wil
Multimodal large language models (MLLMs) have achieved remarkable performance across a wide range of vision-language tasks. However, their ability in low-level visual perception, particularly in detecting fine-grained visual discrepancies, remains underexplored and lacks systematic analysis.In this
We show that a language model’s ability to predict text is tightly linked to the breadth of its embedding space: models that spread their contextual representations more widely tend to achieve lower perplexity. Concretely, we find that representation dispersion—the average pairwise cosine distance a…
The proliferation of Large Language Models (LLMs) has raised concerns over training data privacy. Membership Inference Attacks (MIA), aiming to identify whether specific data was used for training, pose significant privacy risks. However, existing MIA methods struggle to address the scale and comple
Hypergraphs provide a natural and expressive framework for modeling high-order relationships, enabling the representation of group-wise interactions beyond pairwise connections. While hypergraph neural networks (HNNs) have shown promise for learning on such structures, existing models often rely on
With the rapid development of large multimodal models, reliable judge and critic models have become essential for open-ended evaluation and preference alignment, providing pairwise preferences, numerical scores, and explanatory justifications for assessing model-generated responses. However, existin
Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefits of agentic behavior. We introduce PyVision-RL, a reinforcement learning framework for open-weight multimodal models th…
Training large language models for code generation requires selecting high-quality data from solution pools where each problem admits multiple correct implementations. Conventional studies on data selection hold that sophisticated strategies that employ various optimization objectives, such as diver…
High-quality 3D garment reconstruction plays a crucial role in mitigating the sim-to-real gap in applications such as digital avatars, virtual try-on and robotic manipulation. However, existing garment reconstruction methods typically rely on unstructured representations, such as 3D Gaussian Splats,
Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this “LLM-as-a-Judge” paradigm is costly, opaque, and sensitive to prompt design. In this work, we investigate whether smaller models can serve as efficient evaluators by leveraging internal representations…
Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety fine-tuning or \textit{aggressive} token manipulations, incurring subs…
Graph Neural Networks (GNNs) have achieved remarkable successes in graph analysis due to the Message-Passing (MP) mechanism, yet they struggle with heterophilic graphs where connected nodes often have distinct labels or dissimilar attributes. Graph Contrastive Learning (GCL) serves as a promising ap…
In this paper, we develop a novel local graph pooling method, namely the Separated Subgraph-based Hierarchical Pooling (SSHPool), for graph classification. We commence by assigning the nodes of a sample graph into different clusters, resulting in a family of separated subgraphs. We individually empl
Recent advancements in multimodal large language models (MLLMs) and video agent systems have significantly improved general video understanding. However, when applied to scientific video understanding and educating--a domain that demands external professional knowledge integration and rigorous step-
Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending generation to long videos. Recent work has explored autoregressive…
Hyperedge prediction plays a central role in hypergraph learning, enabling the inference of high-order relations among multiple entities. However, existing methods often rely on a simplistic flat set assumption, treating candidate hyperedges as unstructured collections of nodes and neglecting their
The advancement of intelligent agents has revolutionized problem-solving across diverse domains, yet solutions for personalized fashion styling remain underexplored, which holds immense promise for promoting shopping experiences. In this work, we present StyleTailor, the first collaborative agent fr
The deployment of Large Language Models is constrained by the memory and bandwidth demands of static weights and dynamic Key-Value cache. SVD-based compression provides a hardware-friendly solution to reduce these costs. However, existing methods suffer from two key limitations: some are suboptimal …
This paper presents the first study on the impact of audio watermarking on spoofing countermeasures. While anti-spoofing systems are essential for securing speech-based applications, the influence of widely used audio watermarking, originally designed for copyright protection, remains largely unexpl…
Hypergraph contrastive learning is an effective paradigm for representation learning on higher-order relational data, yet existing methods largely ignore that hyperedges link nodes with multi-level semantics. Standard contrastive objectives emphasize instance discrimination via hyperspherical unifor…
Unified multimodal models (UMMs) have emerged as a powerful paradigm in fundamental cross-modality research, demonstrating significant potential in both image understanding and generation. However, existing research in the face domain primarily faces two challenges: **(1) fragmentation development**…
Latent generative modeling has emerged as the dominant paradigm for Diffusion Transformers (DiT), where a pretrained autoencoder compresses image pixels into a latent space to facilitate the diffusion process. Recently, the use of semantic encoders within autoencoders (AEs) has gained attention, yet
While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm for visual generation remains largely unexplored. Current open-source preference datasets typically contain substantial conflicting preference patterns, where winners excel in some…
Current auto-regressive models can generate high-quality, topologically precise meshes; however, they necessitate thousands—or even tens of thousands—of next-token predictions during inference, resulting in substantial latency. We introduce XSpecMesh, a quality-preserving acceleration method for aut…
Realistic 3D city generation is fundamental to a wide range of applications, including virtual reality and digital twins. However, most existing methods rely on training a single diffusion model, which limits their ability to generate personalized and boundless city-scale scenes. In this paper, we p
This paper presents a comprehensive theoretical analysis of the learnability of neuro-symbolic (NeSy) tasks within hybrid systems. We characterize the learnability of NeSy tasks by their derived constraint satisfaction problems (DCSPs), demonstrating that a task is learnable if and only if its co…
Passenger demand forecasting helps optimize vehicle scheduling, thereby improving urban efficiency. Recently, attention-based methods have been used to adequately capture the dynamic nature of spatio-temporal data. However, existing methods that rely on heuristic masking strategies cannot fully adap
In this paper, we propose a new model to learn Adaptive Kernel-based Representations (AKBR) for graph classification. Unlike state-of-the-art R-convolution graph kernels that are defined by merely counting any pair of isomorphic substructures between graphs and cannot provide an end-to-end learning
Large Language Model (LLM) agents have demonstrated remarkable generalization capabilities across multi-domain tasks. Existing agent tuning approaches typically employ supervised finetuning on entire expert trajectories. However, behavior-cloning of full trajectories can introduce expert bias and we…
Heterophilic graph neural networks (GNNs) have gained prominence for their ability to learn effective representations in graphs with diverse, attribute-aware relationships. While existing methods leverage attribute inference during message passing to improve performance, they often struggle with cha
Graph Neural Networks (GNNs) are powerful tools for graph learning, but one of the important challenges is how to effectively extract representations for graph-level tasks. In this paper, we propose an end-to-end Simple Clustering Hierarchical Pooling (SCHPool) operation, which is based on Top-K nod
Evaluating large language models (LLMs) is costly: it requires the generation and examination of LLM outputs on a large-scale benchmark of various tasks. This paper investigates how to efficiently reduce the tasks used to benchmark LLMs without affecting the evaluation quality. Our study reveals tha…
To enhance controllability in text-to-image generation, ControlNet introduces image-based control signals, while ControlNet++ improves pixel-level cycle consistency between generated images and the input control signal. To avoid the prohibitive cost of back-propagating through the sampling process,…
Discrete speech representations have gained significant success in a variety of speech-related tasks. Among these, Neural Audio Codec (NAC), which serves as a compressed form of audio signals, have proven effective in speech AIGC applications. Moreover, we believe that the speaker information can be…
Color plays an important role in human perception and usually provides critical clues in visual reasoning. However, it is unclear whether and how vision-language models (VLMs) can perceive, understand, and leverage color as humans. This paper introduces ColorBench, an innovative benchmark meticulous…
Time series anomaly detection plays a crucial role in a wide range of real-world applications. Given that time series data can exhibit different patterns at different sampling granularities, multi-scale modeling has proven beneficial for uncovering latent anomaly patterns that may not be apparent at…
Inderscience is a global company, a dynamic leading independent journal publisher disseminates the latest research across the broad fields of science, engineering and technology; management, public and business administration; environment, ecological economics and sustainable development; computing,…
Graph-based representations are powerful tools for analyzing structured data. In this paper, we propose a novel model to learn Deep Hierarchical Attention-based Kernelized Representations (DHAKR) for graph classification. To this end, we commence by learning an assignment matrix to hierarchically ma…
In this paper, we propose a family of novel Deep Hierarchical Transitive-Aligned Graph Kernels (DHTAGK) for graph classification. To this end, we commence by developing a new Hierarchical Aligned Graph Auto-Encoder (HA-GAE) to construct transitive-aligned embedding graphs that encapsulate the struct
Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). Among RLHF methods, Group Relative Policy Optimization (GRPO) has gained attention for its simplicity and strong performance, notably eliminating the need for a lea
Hypergraphs provide a flexible framework for modeling high-order (complex) interactions among multiple entities, extending beyond traditional pairwise correlations in graph structures. However, deep hypergraph neural networks (HGNNs) often face the challenge of oversmoothing with increasing depth, s…
Recent studies on large language models (LLMs) and large multimodal models (LMMs) have demonstrated promising skills in various domains including science and mathematics. However, their capability in more challenging and real-world related scenarios like engineering has not been systematically studi…
Federated learning research has recently shifted from Convolutional Neural Networks (CNNs) to Vision Transformers (ViTs) due to their superior capacity. ViTs training demands higher computational resources due to the lack of 2D inductive biases inherent in CNNs. However, efficient federated training…
Graph Neural Networks (GNNs) have emerged as powerful tools for graph learning, and one key challenge arising in GNNs is the development of effective pooling operations for learning meaningful graph representations. In this paper, we propose a novel Edge-Node Attention-based Hierarchical Pooling (EN…
The growing demand for personalized learning underscores the importance of accurately predicting students' future performance to support tailored education and optimize instructional strategies. Traditional approaches predominantly focus on temporal modeling using historical response records and lea…
Event cameras capture visual information as asynchronous pixel change streams, excelling in challenging lighting and high-dynamic scenarios. Existing multimodal large language models (MLLMs) concentrate on natural RGB images, failing in scenarios where event data fits better. In this paper, we intro…
A lightweight Convolutional Neural Network (CNN) typically requires knowledge transfer from a large powerful network before it is employed in resource-limited edge devices. Vision Transformer (ViT) possesses an unparalleled capability for global modeling but remains largely unexplored in Knowledge D…
The over-smoothing has emerged as a major challenge in the development of Graph Neural Networks (GNNs). While existing state-of-the-art methods effectively mitigate the diminishing distance between nodes and improve the performance of node classification, they tend to be elusive for graph-level task
Vision-Language-Action (VLA) models have significantly advanced robotic manipulation by enabling robots to interpret language instructions for task execution. However, training these models often relies on large-scale user-specific data, raising concerns about privacy and security, which in turn lim…
In this paper, we propose a Hierarchical Aligned Subtree Convolutional Network (HA-SCN) for graph classification. Our idea is to transform graphs of arbitrary sizes into fixed-sized aligned graphs and construct a normalized K-layer m-ary subtree for each node in the aligned graphs. By sliding convol
Recent advancements in diffusion-based technologies have made significant strides, particularly in identity-preserved portrait generation (IPG). However, when using multiple reference images from the same ID, existing methods typically produce lower-fidelity portraits and struggle to customize face…
Hypergraphs offer a natural paradigm for modeling complex systems with multi-way interactions. Hypergraph neural networks (HGNNs) have demonstrated remarkable success in learning from such higher-order relational data. While such higher-order modeling enhances relational reasoning, the effectiveness…
With the growing adoption of Hypergraph Neural Networks (HNNs) to model higher-order relationships in complex data, concerns about their security and robustness have become increasingly important. However, current security research often overlooks the unique structural characteristics of hypergraph…
Recent advancements in implicit 3D reconstruction methods, e.g., neural rendering fields and Gaussian splatting, have primarily focused on novel view synthesis of static or dynamic objects with continuous motion states. However, these approaches struggle to efficiently model a human-interactive obje
In this paper, we explore cooperative sensing and communication within cell-free integrated sensing and communication (ISAC) systems. Specifically, multiple transmit access points (APs) collaboratively serve multiple communication users while simultaneously illuminating a potential target, with a se…
Class-incremental learning (CIL) enables models to learn new classes continually without forgetting previously acquired knowledge. Multi-label CIL (MLCIL) extends CIL to a real-world scenario where each sample may belong to multiple classes, introducing several challenges: label absence, which leads…
Multimodal emotion recognition aims to identify emotions by integrating multimodal features derived from spoken utterances. However, existing work often neglects the calibration of conversational entities, focusing mainly on extracting potential intra- or cross-modal information. This leads to the u
Video large language models (Video-LLMs) have made significant progress in understanding videos. However, processing multiple frames leads to lengthy visual token sequences, presenting challenges such as the limited context length cannot accommodate the entire video, and the inclusion of irrelevant…
The out-of-distribution (OOD) detection on graph-structured data is crucial for deploying graph neural networks securely in open-world scenarios. However, existing methods have overlooked the prevalent scenario of multi-label classification in real-world applications. In this work, we investigate th…
Finetuning large language models with a variety of instruction-response pairs has enhanced their capability to understand and follow instructions. Current instruction tuning primarily relies on teacher models or human intervention to generate and refine the instructions and responses for training, w…
High-quality training triplets (instruction, original image, edited image) are essential for instruction-based image editing. Predominant training datasets (e.g., InsPix2Pix) are created using text-to-image generative models (e.g., Stable Diffusion, DALL-E) which are not trained for image editing. A…
The problem of over-smoothing has emerged as a fundamental issue for Graph Convolutional Networks (GCNs). While existing efforts primarily focus on enhancing the discriminability of node representations for node classification, they tend to overlook the over-smoothing at the graph level, significant…
Video large language models (ViLLMs) excel in general video understanding, e.g., recognizing activities like talking and eating, but struggle with identity-aware comprehension, such as "Wilson is receiving chemotherapy" or "Tom is discussing with Sarah", limiting their applicability in smart healthc…
As multi-modal large language models (MLLMs) frequently exhibit errors when solving scientific problems, evaluating the validity of their reasoning processes is critical for ensuring reliability and uncovering fine-grained model weaknesses. Since human evaluation is laborious and costly, prompting M…
Large language models (LLMs) have shown remarkable effectiveness across various domains, with data augmentation methods utilizing GPT for synthetic data generation becoming prevalent. However, the quality and utility of augmented data remain questionable, and current methods lack clear metrics for e…
Large Language Models (LLMs) have demonstrated exceptional performance in code generation, becoming increasingly vital for software engineering and development. Recently, Chain-of-Thought (CoT) has proven effective for complex tasks by prompting LLMs to reason step-by-step and provide a final answer…
Large language models (LLMs) still lack delicate controllability over their responses, which is critical to enhancing their performance and the user experience. However, curating supervised fine-tuning (SFT) datasets to improve LLM controllability usually relies on human experts or proprietary LLMs,…
Panoptic Scene Graph Generation (PSG) integrates instance segmentation with relation understanding to capture pixel-level structural relationships in complex scenes. Although recent approaches leveraging pre-trained vision-language models (VLMs) have significantly improved performance in the open-vo…
The explosive growth of generative video models has amplified the demand for reliable copyright preservation of AI-generated content. Despite its popularity in image synthesis, invisible generative watermarking remains largely underexplored in video generation. To address this gap, we propose Safe-S…
Video generation techniques have made remarkable progress, promising to be the foundation of interactive world exploration. However, existing video generation datasets are not well-suited for world exploration training as they suffer from some limitations: limited locations, short duration, static s…
The rapid advancement of large language models (LLMs) has significantly enhanced their reasoning abilities, enabling increasingly complex tasks. However, these capabilities often diminish in smaller, more computationally efficient models like GPT-2. Recent research shows that reasoning distillation…
Exemplar-Free Class-Incremental Learning (EFCIL) aims to sequentially learn from distinct categories without retaining exemplars but easily suffers from catastrophic forgetting of learned knowledge. While existing EFCIL methods leverage knowledge distillation to alleviate forgetting, they still face…
We present a framework for pre-training of 3D hand pose estimation from in-the-wild hand images sharing with similar hand characteristics, dubbed SiMHand. Pre-training with large-scale images achieves promising results in various tasks, but prior methods for 3D hand pose pre-training have not fully…
The learnware paradigm aims to establish a learnware market such that users can build their own models by reusing appropriate existing models in the market without starting from scratch. It is often the case that a single model is insufficient to fully satisfy the user's requirement. Meanwhile, offe…
Due to the challenges of manually collecting accurate editing data, existing datasets are typically constructed using various automated methods, leading to noisy supervision signals caused by the mismatch between editing instructions and original-edited image pairs. Recent efforts attempt to improve…
Self-supervised depth estimation from monocular cameras in diverse outdoor conditions, such as daytime, rain, and nighttime, is challenging due to the difficulty of learning universal representations and the severe lack of labeled real-world adverse data.Previous methods either rely on synthetic inp…
In this work, we address the test-time adaptation challenge in graph neural networks (GNNs), focusing on overcoming the limitations in flexibility and generalization inherent in existing data-centric approaches. To this end, we propose a novel research problem, test-time graph neural dataset search,…
Recently, there has been growing interest in leveraging large language models (LLMs) to generate symbolic world models from textual descriptions. Although LLMs have been extensively explored in the context of world modeling, prior studies encountered several challenges, including evaluation randomne…
This paper investigates the role of explicit thinking process in rule-based reinforcement fine-tuning (RFT) for multi-modal large language models (MLLMs). We first extend \textit{Thinking-RFT} to image classification task, using verifiable rewards for fine-tuning~(FT). Experiments show {Thinking-RFT…
While Large Reasoning Models (LRMs) generate extensive chain-of-thought reasoning, we lack a principled framework for understanding how these thoughts are structured. In this paper, we introduce a novel approach by applying Schoenfeld’s Episode Theory, a classic cognitive framework for human mathema
Reinforcement learning (RL) has shown great effectiveness for fine-tuning large language models (LLMs) using tasks that are challenging yet easily verifiable, such as math reasoning or code generation. However, extending this success to visual perception in vision–language models (VLMs) has been imp…
Invisible watermarking is widely used to protect digital images from unauthorized use. Accurate assessment of watermarking efficacy is crucial for advancing algorithmic development. However, existing statistical metrics, such as PSNR, rely on access to original images, which are often unavailable in…
What makes a difference in the post-training of LLMs? We investigate the training patterns of different layers in large language models (LLMs) through the lens of the gradient. We are specifically interested in how fast vs. slow thinking affects the layer-wise gradients, given the recent popularity…
Hypergraph neural networks (HNNs) have shown promise in handling tasks characterized by high-order correlations, achieving notable success across various applications. However, there has been limited focus on heterophilic hypergraph learning (HHL), in contrast to the increasing attention given to gr…
The target of video moment retrieval (VMR) is predicting temporal spans within a video that semantically match a given linguistic query. Existing VMR methods based on multimodal large language models (MLLMs) overly rely on expensive high-quality datasets and time-consuming fine-tuning. Although some…
In contrast to human speech, machine-generated sounds of the same type often exhibit consistent frequency characteristics and discernible temporal periodicity. However, leveraging these dual attributes in anomaly detection remains relatively under-explored. In this paper, we propose an automated dua…
At present, the use of underwater robots to replace underwater manual work is a future development direction. The complex and changeable underwater environment brings great difficulties to the operation of robots. In order to improve the problem of color distortion and degradation of sea cucumber im
Weakly supervised learning aims to make machine learning more powerful when the perfect supervision is unavailable, and has attracted much attention from researchers. Among the various scenarios of weak supervision, one of the most challenging cases is learning from multiple unlabeled (U) datasets w…
Intra Block Copy (IBC) and Intra Template Matching Prediction (IntraTMP) are two efficient algorithms to sufficiently exploit the correlation in the same picture. Block Vector (BV) is used to represent the displacement between the current block and its reference within the same picture. The BV infor…
Abductive Learning (ABL) is a promising framework for integrating sub-symbolic perception and logical reasoning through abduction. In this case, the abduction process provides supervision for the perception model from the background knowledge. Nevertheless, this process naturally contains uncertaint…
Making LLMs speak for different, especially minority groups of people, and generate statements supporting their diverse or even controversial perspectives is critical to creating an inclusive environment. However, existing LLMs lack sufficient controllability to the stance of their generated content…
Personal voice activity detection (PVAD) is gradually used in speech assistants. Traditional PVAD schemes extract the target speaker’s embedding from existing query reference speech through a pre-trained speaker verification model. Consequently, the performance of the PVAD model may suffer if the qu…
In offline Reinforcement Learning (RL), the pre-trained policies are utilized for initialization and subsequent online fine-tuning. However, existing methods suffer from instability and low sample efficiency compared to pure online learning. This paper identifies these limitations stemming from dire…
In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. Recognizing this, we introduce a self-guided methodology for LLMs to autonomously discern and select cherry samples from open-source datasets, effectively minimizing manual curat…
Graph Auto-Encoders (GAEs) are powerful tools for graph representation learning. In this paper, we develop a novel Hierarchical Cluster-based GAE (HC-GAE), that can learn effective structural characteristics for graph data analysis. To this end, during the encoding process, we commence by utilizing…
Spectral Graph Neural Networks (GNNs), alternatively known as *graph filters*, have gained increasing prevalence for heterophily graphs. Optimal graph filters rely on Laplacian eigendecomposition for Fourier transform. In an attempt to avert prohibitive computations, numerous polynomial filters have…
This paper introduces an innovative deep learning framework for parallel voice conversion to mitigate inherent risks associated with such systems. Our approach focuses on developing an invertible model capable of countering potential spoofing threats. Specifically, we present a conversion model that…
In this paper, we introduce a novel approach that unifies Automatic Speech Recognition (ASR) and speaker diarization in a cohesive framework. Utilizing the synergies between the two tasks, our method effectively extracts speaker-specific information from the lower layers of a pretrained Conformer-ba…
Large Language Models (LLMs) have shown significant promise in various applications, including zero-shot and few-shot learning. However, their performance can be hampered by inherent biases. Instead of traditionally sought methods that aim to minimize or correct these biases, this study introduces a…
Understanding communication and information processing among brain regions of interest (ROIs) is highly dependent on long-range connectivity, which plays a crucial role in facilitating diverse functional neural integration across the entire brain. However, previous studies generally focused on the s…
Utilizing the pseudo-labeling algorithm with large-scale unlabeled data becomes crucial for semi-supervised domain adaptation in speaker verification tasks. In this paper, we propose a novel pseudo-labeling method named Multi-objective Progressive Clustering (MoPC), specifically designed for semi-su…
In this work, we develop a new Quantum-based Matching Kernel (QBMK) for un-attributed graphs, by computing the kernel-based similarity between the quantum Shannon entropies of aligned vertices through the Continuous-time Quantum Walk (CTQW). The theoretical analysis reveals that the proposed QBMK ke…
In recent years, neural network-based Wake Word Spotting achieves good performance on clean audio samples but struggles in noisy environments. Audio-Visual Wake Word Spotting (AVWWS) receives lots of attention because visual lip movement information is not affected by complex acoustic scenes. Previo…
Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality. Many recent methods focus on improving the data quality but often overlook the compatibility of the…
Multi-Modal automatic speech recognition (ASR) techniques aim to leverage additional modalities to improve the performance of speech recognition systems. While existing approaches primarily focus on video or contextual information, the utilization of extra supplementary textual information has been…
Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But it also leads to extra cost and computation due to the involv…
Recent advances in fine-tuning Vision-Language Models (VLMs) have witnessed the success of prompt tuning and adapter tuning, while the classic model fine-tuning on inherent parameters seems to be overlooked. It is believed that fine-tuning the parameters of VLMs with few-shot samples corrupts the pr…
Unsupervised multimodal machine translation (UMMT) aims to leverage vision information as a pivot between two languages to achieve better performance on low-resource language pairs. However, there is presently a challenge: how to handle alignment between distant language pairs (DLPs) in UMMT. To thi…
In this paper, we introduce a large-scale and high-quality audiovisual speaker verification dataset, named VoxBlink. We propose an innovative and robust automatic audio-visual data mining pipeline to curate this dataset, which contains 1.45M utterances from 38K speakers. Due to the inherent nature o…
The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and fine-tuning procedure in existing practices, which implicitly limi…
In this paper, we propose a convolutional neural network (CNN) filter for reference picture resampling (RPR)-based super-resolution (SR) with wavelet decomposition. The proposed CNN filter takes the low resolution (LR) reconstructed frame (Rec<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns…
High resolution (HR) videos are easy to go beyond the band-width limit during transmission after encoding. Downsampling followed by upsampling is a well-known strategy for compressing HR videos with limited bandwidth. Versatile video coding (VVC) provides a reference picture resampling (RPR) functio…
To alleviate the burden of software maintenance, bug localization, which aims to automatically locate the buggy source files based on the bug report, has drawn significant attention in the software mining community. Recent studies indicate that the program structure in source code carries more seman…
This paper focuses on federated semi-supervised learning (FSSL), assuming that few clients have fully labeled data (labeled clients) and the training datasets in other clients are fully unlabeled (unlabeled clients). Existing methods attempt to deal with the challenges caused by not independent and…
Discriminability and transferability are two goals of feature learning for domain adaptation (DA), as we aim to find the transferable features from the source domain that are helpful for discriminating the class label in the target domain. Modern DA approaches optimize discriminability and transfera…
Despite the great performance of language identification (LID), there is a lack of large-scale singing LID databases to support the research of singing language identification (SLID). This paper proposed a over 3200 hours dataset used for singing language identification, called Slingua. As the basel…
Recently, open-vocabulary learning has emerged to accomplish segmentation for arbitrary categories of text-based descriptions, which popularizes the segmentation system to more general-purpose application scenarios. However, existing methods devote to designing specialized architectures or parameter…
We investigate the expressive power of depth-2 bandlimited random neural networks. A random net is a neural network where the hidden layer parameters are frozen with random assignment, and only the output layer parameters are trained by loss minimization. Using random weights for a hidden layer is a…
An automatic speaker verification system aims to verify the speaker identity of a speech signal. However, a voice conversion system could manipulate a person’s speech signal to make it sound like another speaker’s voice and deceive the speaker verification system. Most countermeasures for voice conv…
The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The generators formulate the answer based on the documents retrieved by the retriever. Incorporating Large Language Models (LLMs) as generators is beneficial due to their ad…
This paper proposes to pretrain Conformer with automatic speech recognition (ASR) task for speaker verification. Conformer combines convolution neural network (CNN) and Transformer model for modeling local and global features, respectively. Recently, multi-scale feature aggregation Conformer (MFA-Co…
Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks. First, they may compromise temporal dynamics in input videos, which are critical for accurate action recognition. Seco…
In this paper, we address a special scenario of semi-supervised learning, where the label missing is caused by a preceding filtering mechanism, i.e., an instance can enter a subsequent process in which its label is revealed if and only if it passes the filtering mechanism. The rejected instances are…
Graph convolutional networks (GCN) are viewed as one of the most popular representations among the variants of graph neural networks over graph data and have shown powerful performance in empirical experiments. That l2-based graph smoothing enforces the global smoothness of GCN, while (soft) l1-base…
Target-speaker voice activity detection is currently a promising approach for speaker diarization in complex acoustic environments. This paper presents a novel Sequence-to-Sequence Target-Speaker Voice Activity Detection (Seq2Seq-TSVAD) method that can efficiently address the joint modeling of large…
This paper further explores our previous wake word spotting system ranked 2-nd in Track 1 of the MISP Challenge 2021. First, we investigate a robust unimodal approach based on 3D and 2D convolution and adopt the simple attention module (SimAM) for our system to improve performance. Second, we explor…
This paper describes the system developed by the WHU-Alibaba team for the Multimodal Information Based Speech Processing (MISP) 2022 Challenge. We extend the Sequence-to-Sequence Target-Speaker Voice Activity Detection framework to simultaneously detect multiple speakers’ voice activities from audio…
The present paper proposes a waveform boundary detection system for audio spoofing attacks containing partially manipulated segments. Partially spoofed/fake audio, where part of the utterance is replaced, either with synthetic or natural audio clips, has recently been reported as one scenario of aud…
In this letter, the 3-D inter-robot relative localization problem is addressed using noise-corrupted odometric and distance measurements. Unlike the existing solutions, we are devoted to providing a relative localization method that has an “overall best performance,” which means that the tradeoffs b
DukeECE. As the highly overlapped speech exists in the dataset, we employ an x-vector-based target-speaker voice activity detection (TS-VAD) to find the overlap between speakers. Firstly, we separately train a single-channel model for each of the 8 channels and fuse the results. In addition, we also…
Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from severe performance degeneration under limited expert data. Including a learned dynamics model can potentially improve the s…
Most real-world problems that machine learning algorithms are expected to solve face the situation with (1) unknown data distribution; (2) little domain-specific knowledge; and (3) datasets with limited annotation. We propose Non-Parametric learning by Compression with Latent Variables (NPC-LV), a l…
In this paper, we propose an end-to-end target-speaker voice activity detection (E2E-TS-VAD) method for speaker diarization. First, a ResNet-based network extracts the frame-level speaker embeddings from the acoustic features. Then, the L2-normalized frame-level speaker embeddings are fed to the tra…
"In this paper, we propose a two-stage omnidirectional depth estimation framework with multi-view 360-degree cameras. The framework first estimates the depth maps from different camera pairs via omnidirectional stereo matching and then fuses the depth maps to achieve robustness against mud spots, wa…
"Albeit with varying degrees of progress in the field of Semi-Supervised Semantic Segmentation, most of its recent successes are involved in unwieldy models and the lightweight solution is still not yet explored. We find that existing knowledge distillation techniques pay more attention to pixel-lev…
This paper presents a multi-granularity method for source code summarization, which generates a concise functional description for the given code snippet. We notice that skilled programmers write and read source codes hierarchically and pay close attention to conceptual entities like statements, tok…
Nowadays, as more and more systems achieve good performance in traditional voice conversion (VC) tasks, people’s attention gradually turns to VC tasks under extreme conditions. In this paper, we propose a novel method for zero-shot voice conversion. We aim to obtain intermediate representations for…
Recently, the attention mechanism such as squeeze-and-excitation module (SE) and convolutional block attention module (CBAM) has achieved great success in deep learning-based speaker verification system. This paper introduces an alternative effective yet simple one, i.e., simple attention module (Si…
This paper describes the system developed by the DKU team for the MISP Challenge 2021. We present a two-stage approach consisting of end-to-end neural networks for the audio-visual wake word spotting task. We first process audio and video data to give them a similar structure and then train two unim…
With the development of deep learning, automatic speaker verification has made considerable progress over the past few years. However, to design a lightweight and robust system with limited computational resources is still a challenging problem. Traditionally, a speaker verification system is symmet…
Matrix-based Intra Prediction (MIP) is an effective coding algorithm in H.266/Versatile Video Coding (VVC) which is originated by Neural Networks (NN). With the requirement of low complexity, MIP is conducted by a matrix-vector multiplication. To handle with the diversity of video content, 30 matric…
Learning effective reinforcement learning (RL) policies to solve real-world complex tasks can be quite challenging without a high-fidelity simulation environment. In most cases, we are only given imperfect simulators with simplified dynamics, which inevitably lead to severe sim-to-real gaps in RL po…
In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing agreement between different segments within an utterance via a cont…
This paper presents a new approach for assembling graph neural networks based on framelet transforms. The latter provides a multi-scale representation for graph-structured data. We decompose an input graph into low-pass and high-pass frequencies coefficients for network training, which then defines…
Multi-task dense retrieval models can be used to retrieve documents from a common corpus (e.g., Wikipedia) for different open-domain question-answering (QA) tasks. However, Karpukhin et al. (2020) shows that jointly learning different QA tasks with one dense model is not always beneficial due to cor…
Transformers are powerful for sequence modeling. Nearly all state-of-the-art language models and pre-trained language models are based on the Transformer architecture. However, it distinguishes sequential tokens only with the token position index. We hypothesize that better contextual representation…
To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors. In this paper, we seek to achieve the similar goal but do not involve more human efforts. T…
Code summarization aims to summarize code functionality as high-level nature language descriptions to assist in code comprehension. Recent approaches in this field mainly focus on generating summaries for code with precise identifier names, in which meaningful words can be found indicating code fun…
In this paper, we address unsupervised chunking as a new task of syntactic structure induction, which is helpful for understanding the linguistic structures of human languages as well as processing low-resource languages. We propose a knowledge-transfer approach that heuristically induces chunk labe…
This paper introduces an obstacle-crossing strategy, and the self-reconfiguration algorithm for a new class of modular robots called the rolling sphere, which can fit obstacles represented by cubes of different sizes due to the chain connection of multiple spheres. For the self-reconfiguration of th…
This paper proposes a novel modular selfreconfigurable robot (MSRR) "FreeBOT", which can be connected freely at any point on other robots. FreeBOT is mainly composed of two parts: a spherical ferromagnetic shell and an internal magnet. The connection between the modules is genderless and instant, si…
This paper presents a far-field text-dependent speaker verification database named HI-MIA. We aim to meet the data requirement for far-field microphone array based speaker verification since most of the publicly available databases are single channel close-talking and text-independent. The database…
Deep Graph Neural Networks (GNNs) are useful models for graph classification and graph-based regression tasks. In these tasks, graph pooling is a critical ingredient by which GNNs adapt to input graphs of varying size and structure. We propose a new graph pooling operation based on compressive Haar…
Under the excitation of acoustic radiation, the amount of energy absorbed and rebounded by cells have the relationship with mechanical properties, e.g. stiffness, shape, weight and so on. In this paper, a femtosecond laser-activated micro-detector is designed to convert this relationship into an ele…
Graph neural networks (GNNs) extends the functionality of traditional neural networks to graph-structured data. Similar to CNNs, an optimized design of graph convolution and pooling is key to success. Borrowing ideas from physics, we propose a path integral based graph neural networks (PAN) for clas…
In this paper, the 2D robot-to-robot relative pose (position and orientation) estimation problem based on ego-motion and noisy distance measurements is considered. We address this problem using an optimization-based method, which does not require complicated numerical analysis while yields no inferi…
Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding of the noisy utterance. Specifically, the network is trained…
Pitch plays a significant role in understanding a tone based language like Mandarin. In this paper, we present a new method that estimates F0 contour for electrolaryngeal (EL) speech enhancement in Mandarin. Our system explores the usage of phonetic feature to improve the quality of EL speech. First…