43 accepted papers
We propose AUV, a unified neural audio codec with a single codebook, which enables a favourable reconstruction of speech and further extends to general audio, including vocal, music, and sound. AUV is capable of tackling any 16 kHz mixed-domain audio segment at bit rates around 700 bps. To accomplis…
Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size. To address this, speculative decoding emerges as a solution, enabling the simultaneous generation and validation of multiple tokens. While recent approaches like EAGLE…
Endoscopic video analysis is essential for early gastrointestinal screening but remains hindered by limited high-quality annotations. While self-supervised video pre-training shows promise, existing methods developed for natural videos prioritize dense spatio-temporal modeling and exhibit motion bia
Lipschitz-based certification offers efficient, deterministic robustness guarantees but has struggled to scale in model size, training efficiency, and ImageNet performance. We introduce \emph{LipNeXt}, the first \emph{constraint-free} and \emph{convolution-free} 1-Lipschitz architecture for certifie…
Multimodal large language models (MLLMs) have achieved remarkable success across diverse applications, from autonomous driving to document understanding. As these models are deployed in safety-critical contexts, understanding their adversarial robustness becomes crucial. However, current evaluations
Recent advances in diffusion models have greatly improved pose-driven character animation. However, existing methods are limited to spatially aligned reference-pose pairs with matched skeletal structures. Handling reference-pose misalignment remains unsolved. To address this, we present One-to-All A
Accurate segmentation of ultra-high-resolution (UHR) images, which often exceed tens of millions of pixels, is critically important in domains such as remote sensing and biomedical imaging. However, acquiring pixel-level annotations for such high-resolution images is prohibitively expensive and labo
Large Language Models are rapidly becoming core components of modern software development workflows, yet ensuring code security remains challenging. Existing vulnerability detection pipelines either rely on static analyzers or use LLM/GNN-based detectors trained with coarse program-level supervision…
We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and input preprocessing pipeline. The key idea is a task-level side channel induced by ViT-style patchification: when a synthe…
Non-exemplar class incremental learning (NECIL) aims to continuously assimilate new knowledge while retaining previously acquired knowledge in scenarios where prior examples are unavailable. A prevalent strategy within NECIL mitigates knowledge forgetting by freezing the feature extractor after trai…
Current knowledge distillation (KD) methods for semantic segmentation focus on guiding the student to imitate the teacher's knowledge within homogeneous architectures. However, these methods overlook the diverse knowledge contained in architectures with different inductive biases, which is crucial f…
Remote work and online courses have become important methods of knowledge dissemination, leading to a large number of document-based instructional videos. Unlike traditional video datasets, these videos mainly feature rich-text images and audio that are densely packed with information closely tied t…
Connected component (CC) is a proper text shape representation that aligns with human reading intuition. However, CC-based text detection methods have recently faced a developmental bottleneck that their time-consuming post-processing is difficult to eliminate. To address this issue, we introduce an…
Recently, graph invariant learning has become the _de facto_ approach to tackle the Out-of-Distribution (OOD) generalization failure in graph representation learning. They generically follow the framework of invariant risk minimization to capture the invariance of graph data from different environme…
Recent advances in Multi-Modal Large Language Models (M-LLMs) show promising results in video reasoning. Popular Multi-Modal Large Language Model (M-LLM) frameworks usually apply naive uniform sampling to reduce the number of video frames that are fed into an M-LLM, particularly for long context vid…
Data quality and diversity are key to the construction of effective instruction-tuning datasets. With the increasing availability of open-source instruction-tuning datasets, it is advantageous to automatically select high-quality and diverse subsets from a vast amount of data. Existing methods typic…
Detecting small instances within complex backgrounds presents significant challenges for Remote Sensing Object Detection (RSOD). While complex deep networks can enhance feature representation, they often lead to considerable computational burdens. Previous research has proposed dual-stream learning…
Existing diffusion-based video super-resolution (VSR) methods are susceptible to introducing complex degradations and noticeable artifacts into high-resolution videos due to their inherent randomness. In this paper, we propose a noise-robust real-world VSR framework by incorporating self-supervised…
In recent years, many fusion algorithms based on multi-scale transform or neural networks have been proposed to improve medical image fusion (MIF) performance. However, there is still enormous potential to explore the combination of different fusion theories. In this paper, we propose a novel MIF fr…
Recent studies have highlighted the potential of Lipschitz-based methods for training certifiably robust neural networks against adversarial attacks. A key challenge, supported both theoretically and empirically, is that robustness demands greater network capacity and more data than standard trainin…
This paper presents a novel approach to object completion, with the primary goal of reconstructing a complete object from its partially visible components. Our method, named MaskComp, delineates the completion process through iterative stages of generation and segmentation. In each iteration, the ob…
Recent research indicates that large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content. This paper introduces a novel token-level attack method, Adaptive Dense-to-Sparse Constrained Optimization (ADC), which has been shown to successfully jailbreak mult…
Recently, there has been a surge of interest in developing graph neural networks that utilize the invariance principle on graphs to generalize the out-of-distribution (OOD) data. Due to the limited knowledge about OOD data, existing approaches often pose assumptions about the correlation strengths o…
This paper presents FunCodec, a fundamental neural speech codec toolkit, which is an extension of the open-source speech processing toolkit FunASR. FunCodec provides reproducible training recipes and inference scripts for the latest neural speech codec models, such as SoundStream and Encodec. Thanks…
Endoscopic video analysis can effectively assist clinicians in disease diagnosis and treatment, and has played an indispensable role in clinical medicine. Unlike regular videos, endoscopic video analysis presents unique challenges, including complex camera movements, uneven distribution of lesions,…
In multi-sequence Magnetic Resonance Imaging (MRI), the accurate segmentation of the kidney and tumor based on traditional supervised methods typically necessitates detailed annotation for each sequence, which is both time-consuming and labor-intensive. Unsupervised Domain Adaptation (UDA) methods c…
This paper presents a bionic foldable wing that imitates the hind wing of ladybirds. Based on the folding mechanism of the hind wing of ladybirds and the theory of origami, the motion model of the bionic foldable wing is established, yield the motion law of the crease angles and the variation relati…
Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-quality images, audios, and videos. They benefit significantly from extensive pre-training on large-scale datasets, including web-crawled data with paired data and conditions, such as image-text and image-class p…
In this paper, we present a new question-answering (QA) based key-value pair extraction approach, called KVPFormer, to robustly extracting key-value relationships between entities from form-like document images. Specifically, KVPFormer first identifies key entities from all entities in an image with…
Nasopharyngeal carcinoma (NPC) is a malignant tumor with a high incidence. Accurate segmentation of the tumor region in Computed Tomography (CT) images of NPC is the key to treatment. However, the features of uneven grayscale values and hazy boundaries of NPC regions make accurate NPC segmentation p…
Glass is ubiquitous in the real world, and its perception has many applications, including robot navigation and drone tracking. However, due to the transparent property of glass, the interior of a glass area can be any surrounding scene or object, which brings challenges for computer vision. Inspire…
This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the training process and attribute the overlooked phenomenon to two limitations: lack of training emphasis and cascading errors…
In this paper, we propose a novel convolutional neural network (MDR-Net) for ultrasound image segmentation by exploiting multi-decision and deep refinement of the target. Our MDR-Net consists of two main parts, i.e., a multi-decision module (MDM) and a deep refinement module (DRM). Specifically, the…
Unsupervised domain adaptation (UDA) attracts extra attention in medical image processing because no additional labels are required when adapting to different distributions. In this work, we propose a novel unsupervised domain adaptation framework named as Domain Expansion and PseudoLabeling (DEPL).…
Learning how to model global relationships and extract local details is crucial in improving the performance of multi-organ segmentation. Most existing U-shaped structure methods use feature fusion to address these two challenges, but still lack the ability to balance capturing global relationships…
Despite the promise of Lipschitz-based methods for provably-robust deep learning with deterministic guarantees, current state-of-the-art results are limited to feed-forward Convolutional Networks (ConvNets) on low-dimensional data, such as CIFAR-10. This paper investigates strategies for expanding…
In this paper, we propose a novel convolutional neural network based on adaptive multi-scale feature aggregation and boundary-aware for lateral ventricle segmentation (MB-Net), which mainly includes three parts, i.e., an adaptive multi-scale feature aggregation module (AMSFM), an embedded boundary r…
Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an image from noise with sentence embedding, and then refine t…
Accurate and automatic gland segmentation can help pathologists diagnose the malignancy of colorectal cancers. However, it remains a challenging task because of the large morphological differences between the glands and the presence of sticky glands. In this paper, a hybrid feature enhancement netwo…
This paper studies the problem of learning self-supervised representations on videos. In contrast to image modality that only requires appearance information on objects or scenes, video needs to further explore the relations between multiple frames/clips along the temporal dimension. However, the re…
Normalization operations are widely used to train deep neural networks, and they can improve both convergence and generalization in most tasks. The theories for normalization's effectiveness and new forms of normalization have always been hot topics in research. To better understand normalization, o…
Conditional random fields (CRFs) have been shown to be one of the most successful approaches to sequence labeling. Various linear-chain neural CRFs (NCRFs) are developed to implement the non-linear node potentials in CRFs, but still keeping the linear-chain hidden structure. In this paper, we propos…
Biped walking control based on simplified models relies much on online feedback stabilizers to compensate the zero-moment point (ZMP) error which partially comes from the model inconsistency of pattern generation. Inspired by the fact that human improves the performance by practicing a task for mult…