87 accepted papers
Latent Diffusion Models have become a powerful tool for generating high-fidelity unrestricted adversarial examples. However, the existing methods typically perturb only the initial latent or rely on prompt engineering, which is ill-suited to the iterative nature of the diffusion process, plus optimi
Zero-shot singing voice conversion (SVC) transforms a source singer
Diffusion models have advanced fine-grained garment generation, yet balancing controllability, efficiency, and texture fidelity remains challenging. Adapter-based methods often yield incoherent details, while full fine-tuning is computationally expensive and prone to overwriting pretrained priors. T
Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-directed interaction. However, this autonomy introduces a previously unrecognized security risk: agentic interaction fundamentally expands the LLM attack…
Existing machine unlearning methods primarily focus on removing data influence after training completes, which is effective for many scenarios, but a complementary capability is needed when removal requests arise during ongoing training. We propose LMCleaner, an efficient and certified \emph{online}…
Vision--language models such as CLIP have shown strong zero-shot performance, but their reliability degrades in realistic multi-label settings under distribution shift. Standard test-time adaptation (TTA) methods either rely on costly gradient-based updates or adopt lightweight statistical schemes t…
Attention learners, neural networks built on the attention mechanism, e.g., transformers, excel at learning the implicit relationships that relate sequences to their corresponding properties, e.g., mapping a given sequence of tokens to the probability of the next token. However, the learning process…
Although current Video-LLMs achieve impressive performance in video understanding tasks, their autoregressive decoding efficiency remains constrained by the massive number of video tokens. Visual token pruning can partially ease this bottleneck, yet existing approaches still suffer from information
In recent years, RF fingerprinting (RFF) has emerged as a promising technology for wireless device authentication. However, temporal variations in device load and temperature, along with channel effects, lead to inconsistencies in RFF distributions between training and testing phases. As a result,
Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularly for nuanced tasks like emotion control. The policy model can exploit a vanilla Reward Model (RM) by generating acousti…
Embedding-as-a-Service (EaaS) is an effective and convenient deployment solution for addressing various NLP tasks. Nevertheless, recent research has shown that EaaS is vulnerable to model extraction attacks, which could lead to significant economic losses for model providers. For copyright protectio
Fine-tuning vision-language models such as CLIP has become the mainstream paradigm for multi-label image recognition, and prompt tuning is widely adopted due to its lightweight parameter cost and strong transferability. However, we find that when these methods use Binary Cross-entropy as the supervi
As the demand for comprehensive evaluations of diverse model capabilities steadily increases, benchmark suites have correspondingly grown significantly in scale. Despite notable advances in redundancy reduction and subset-level performance prediction, a systematic framework that effectively integrat…
Red-teaming Vision-Language Models is essential for identifying vulnerabilities where adversarial image-text inputs trigger toxic outputs. Existing approaches treat image generation as a black box, providing only terminal toxicity scores while remaining temporally opaque regarding when and how toxic…
Concept erasure aims to prevent image generative models from producing unsafe content while preserving their general generative capability. Meanwhile, next-scale autoregressive (AR) image generation has recently emerged as a new generative paradigm characterized by next-scale prediction, for which c…
Speculative decoding (SD) has emerged as a promising technique to accelerate LLM inference by employing a small, efficient draft model to propose draft tokens in advance, and subsequently validating them in parallel with the large target model. However, the existing SD methods still remain fundament…
Despite their capabilities, large foundation models (LFMs) remain susceptible to adversarial manipulation. Current defenses predominantly rely on the ``locality hypothesis", suppressing isolated neurons or features. However, harmful semantics act as distributed, cross-layer circuits, rendering such …
Diffusion Transformers (DiTs) achieve strong video generation quality but suffer from high inference cost due to dense 3D attention, leading to the development of sparse attention technologies to improve efficiency. However, existing training-free sparse attention methods in video generation still f…
Image-based virtual try-on (VTON) aims to synthesize photorealistic images of a person wearing specified garments. Despite significant progress, building a universal VTON framework that can flexibly handle diverse and complex tasks remains a major challenge. Recent methods explore multi-task VTON fr
Multilingual text-to-image (T2I) models have advanced rapidly in terms of visual realism and semantic alignment, and are now widely utilised. Yet outputs vary across cultural contexts: because language carries cultural connotations, images synthesized from multilingual prompts should preserve cross-
Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanisms driving safety alignment remain unclear despite observed cross-lingual representation transfer.In this paper, we find…
Open-set object detection (OSOD) is highly desirable for robotic manipulation in unstructured environments. However, existing OSOD methods often fail to meet the requirements of robotic applications due to their high computational burden and complex deployment. To address this issue, this paper prop
Methods for story generation with Large Language Models (LLMs) have come into the spotlight recently. We create a novel taxonomy of LLMs for story generation consisting of two major paradigms: (i) independent story generation by an LLM, and (ii) author-assistance for story generation – a collaborati
Sign Language Video Generation (SLVG) seeks to generate identity-preserving sign language videos from spoken language texts. Existing methods primarily rely on the single coarse condition (e.g., skeleton sequences) as the intermediary to bridge the translation model and the video generation model, w…
Recent research showcases the considerable potential of conditional diffusion models for generating consistent stories. However, current methods, which primarily generate stories in a caption-dependent manner, often overlook the importance of contextual consistency and the relevance of frames durin…
Auditing Large Language Models (LLMs) is a crucial and challenging task. In this study, we focus on auditing black-box LLMs without access to their parameters, only to the provided service. We treat this type of auditing as a black-box optimization problem where the goal is to automatically uncover…
Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management. However, the algorithmic backbone of neural networks is brittle to imperceptible perturbations in the system inputs, which were generally kn…
Extracting sentence embeddings from large language models (LLMs) is a practical direction, as it requires neither additional data nor fine-tuning. Previous studies usually focus on prompt engineering to guide LLMs to encode the core semantic information of the sentence into the embedding of the last…
The evolution of video generation techniques, such as Sora, has made it increasingly easy to produce high-fidelity AI-generated videos, raising public concern over the dissemination of synthetic content. However, existing detection methodologies remain limited by their insufficient exploration of te…
Traditional text-to-speech (TTS) systems often face challenges in aligning text and speech, leading to the omission of critical linguistic and acoustic details. This misalignment creates an information gap, which existing methods attempt to address by incorporating additional inputs, but these often…
Image-to-video generation, which aims to generate a video starting from a given reference image, has drawn great attention. Existing methods frequently integrate semantic information from images or simply concatenate images, which often leads to low fidelity and flickering in the generated videos. T…
The diffusion model is widely leveraged for either controllable video generation or video interpolation. As each field has its task-specific problems, it is difficult to merely develop a single model for completing both tasks simultaneously. Moreover, most existing works only support image condition…
The success of the text-guided diffusion model has inspired the development and release of numerous powerful diffusion models within the open-source community. These models are typically fine-tuned on various expert datasets, showcasing diverse denoising capabilities. Leveraging multiple high-qualit…
Most of the federated learning techniques are limited to homogeneous model fusion. With the rapid growth of smart applications on resource-constrained edge devices, it becomes a barrier to accommodate their heterogeneous computing power and memory in the real world. Federated Distillation is a promi…
Recently, 3D head avatar modeling based on 3D Gaussians has demonstrated significant advantages in rendering quality and efficiency, given sufficient data. Some efforts have begun to train prior models on large datasets to develop generalizable 3D Gaussian head avatar modeling methods. Unfortunately…
The complex nonlinear dynamics of hydraulic excavators, such as time delays and control coupling, pose significant challenges to achieving high-precision trajectory tracking. Traditional control methods often fall short in such applications due to their inability to effectively handle these nonlinea
Existing virtual try-on (VTON) methods provide only limited user control over garment attributes and generally overlook essential factors such as face, pose, and scene context. To address these limitations, we introduce the virtual dressing (VD) task, which aims to synthesize freely editable human i…
We propose Intra and Inter Parser-Prompted Transformers (PPTformer) that explore useful features from visual foundation models for image restoration. Specifically, PPTformer contains two parts: an Image Restoration Network (IRNet) for restoring images from degraded observations and a Parser-Prompted…
To address the growing demand for privacy protection in machine learning, we propose an efficient and exact machine unlearning method for Large Models, called LMEraser. LMEraser takes a divide-and-conquer strategy with an adaptive prompt tuning mechanism to isolate data influence effectively. The tr…
Recent advances in conditional diffusion models have shown promise for generating realistic TalkingFace videos, yet challenges persist in achieving consistent head movement, synchronized facial expressions, and accurate lip synchronization over extended generations. To address these, we introduce th…
Creating high-fidelity head avatars from multi-view videos is essential for many AR/VR applications. However, current methods often struggle to achieve high-quality renderings across all head components (e.g., skin vs. hair) due to the limitations of using one single representation for elements with…
Recent large Pre-trained Language Models (PLMs) usually only provide users with the inference APIs, namely the emerging Model-as-a-Service (MaaS) setting. To adapt MaaS PLMs to downstream tasks without accessing their parameters and gradients, some existing methods focus on the output-side adaptatio…
With the rapid advancement of the digital economy, data collaboration between organizations has become a well-established business model, driving the growth of various industries. However, privacy concerns make direct data sharing impractical. To address this, Two-Party Split Learning (a.k.a. Verti…
In domain adaption (DA), joint maximum mean discrepancy (JMMD), as a famous distribution-distance metric, aims to measure joint probability distribution difference between the source domain and target domain, while it is still not fully explored and especially hard to be applied into a subspace-lear…
The effectiveness of large language models (LLMs) in conversational AI is hindered by their reliance on single-turn supervised fine-tuning (SFT) data, which limits contextual coherence in multi-turn dialogues. Existing methods for generating multi-turn dialogue data struggle to ensure both diversity…
Developing reliable defenses against patch attacks on object detectors has attracted increasing interest. However, we identify that existing defense evaluations lack a unified and comprehensive framework, resulting in inconsistent and incomplete assessments of current methods. To address this issue,…
Accurately evaluating the word sense disambiguation (WSD) capabilities of large language models (LLMs) remains challenging, as existing studies primarily rely on single-task evaluations and classification-based metrics that overlook the fundamental differences between generative LLMs and traditional
Creating high-fidelity and editable head avatars is a pivotal challenge in computer vision and graphics, boosting many AR/VR applications. While recent advancements have achieved photorealistic renderings and plausible animation, head editing, especially real-time appearance editing, remains challen…
Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and cost-efficient approach that directly modifies the activations of LL…
Recent advancements in Automatic Prompt Optimization (APO) for text-to-image generation have streamlined user input while ensuring high-quality image output. However, most APO methods are trained assuming a fixed text-to-image model, which is impractical given the emergence of new models. To address…
Safety-critical scenarios are infrequent in natural driving environments but hold significant importance for the training and testing of autonomous driving systems. The prevailing approach involves generating safety-critical scenarios automatically in simulation by introducing adversarial adjustment…
Recent work has showcased the significant potential of diffusion models in pose-guided person image synthesis. However, owing to the inconsistency in pose between the source and target images, synthesizing an image with a distinct pose, relying exclusively on the source image and target pose informa…
As a more challenging domain adaptation setting, universal domain adaptation (UniDA) introduces category shift on top of domain shift, which needs to identify unknown category in the target domain and avoid misclassifying target samples into source private categories. To this end, we propose a novel…
This paper investigates two fundamental problems that arise when utilizing Intrinsic Motivation (IM) for reinforcement learning in Reward-Free Pre-Training (RFPT) tasks and Exploration with Intrinsic Motivation (EIM) tasks: 1) how to design an effective intrinsic objective in RFPT tasks, and 2) how…
This paper proposes UHDformer, a general Transformer for Ultra-High-Definition (UHD) image restoration. UHDformer contains two learning spaces: (a) learning in high-resolution space and (b) learning in low-resolution space. The former learns multi-level high-resolution features and fuses low-high fe…
Although autonomous robots have great potential to boost efficiency and throughput across the whole retail chain, they are mostly being deployed in large warehouses and distribution centers. Deploying robots in stores with customers, such as supermarkets, requires substantially more development effo…
Patch-level non-local self-similarity is an important property of natural images. However, most existing methods do not consider this property into neural networks for image deraining, thus affecting recovery performance. Motivated by this property, we find that there exists significant patch recurr…
Speech emotion recognition (SER) systems aim to recognize human emotional state during human-computer interaction. Most existing SER systems are trained based on utterance-level labels. However, not all frames in an audio have affective states consistent with utterance-level label, which makes it di…
This work presents an effective depth-consistency Self-Prompt Transformer, terms as SelfPromer, for image dehazing. It is motivated by an observation that the estimated depths of an image with haze residuals and its clear counterpart vary. Enforcing the depth consistency of dehazed images with clear…
Domain Generalization (DG) aims to improve the generalization ability of models trained on a specific group of source domains, enabling them to perform well on new, unseen target domains. Recent studies have shown that methods that converge to smooth optima can enhance the generalization performance…
Deep learning methods on graph data have achieved remarkable efficacy across a variety of real-world applications, such as social network analysis and transaction risk detection. Nevertheless, recent studies have illuminated a concerning fact: even the most expressive Graph Neural Networks (GNNs) ar…
Large language models have demonstrated exceptional language understanding capabilities in many NLP tasks. Sparsely activated mixture-of-experts (MoE) has emerged as a promising solution for scaling models while maintaining a constant number of computational operations. Existing MoE models adopt a f…
Automated Essay Scoring (AES) aims to evaluate the quality score for input essays. In this work, we propose a novel unsupervised AES approach ULRA, which does not require groundtruth scores of essays for training. The core idea of our ULRA is to use multiple heuristic quality signals as the pseudo-g…
Multiple instance learning (MIL) is a popular weakly-supervised learning model on the whole slide image (WSI) for AI-assisted pathology diagnosis. The recent advance in attention-based MIL allows the model to find its region-of-interest (ROI) for interpretation by learning the attention weights for…
For deep ordinal classification, learning a well-structured feature space specific to ordinal classification is helpful to properly capture the ordinal nature among classes. Intuitively, when Euclidean distance metric is used, an ideal ordinal layout in feature space would be that the sample cluster…
This letter proposes a learning-based adaptive propulsion control (APC) method for a quadruped robot integrated with thrusters in amphibious environments, allowing it to move efficiently in water while maintaining its ground locomotion capabilities. We designed the specific reinforcement learning me
We propose a novel method, LoLep, which regresses Locally-Learned planes from a single RGB image to represent scenes accurately, thus generating better novel views. Without the depth information, regressing appropriate plane locations is a challenging problem. To solve this issue, we pre-partition t…
We show that raw degradation features can effectively guide deep restoration models, providing accurate degradation priors to facilitate better restoration. While networks that do not consider them for restoration forget gradually degradation during the learning process, model capacity is severely h…
As manual point-wise label is time and labor-intensive for fully supervised large-scale point cloud semantic segmentation, weakly supervised method is increasingly active. However, existing methods fail to generate high-quality pseudo labels effectively, leading to unsatisfactory results. In this p…
As in-the-wild data are increasingly involved in the training stage, machine learning applications become more susceptible to data poisoning attacks. Such attacks typically lead to test-time accuracy degradation or controlled misprediction. In this paper, we investigate the third type of exploitatio…
"Vision Transformers (ViTs) have recently dominated a range of computer vision tasks, yet it suffers from low training data efficiency and inferior local semantic representation capability without appropriate inductive bias. Convolutional neural networks (CNNs) inherently capture regional-aware sema…
We propose for the first time, a novel deep active visuo-tactile cross-modal full-fledged framework for object recognition by autonomous robotic systems. Our proposed network <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">xAVTNet</i> is actively tra
We present a novel self-supervised algorithm named MotionHint for monocular visual odometry (VO) that takes motion constraints into account. A key aspect of our approach is to use an appropriate motion model that can help existing self-supervised monocular VO (SSM-VO) algorithms to overcome issues r…
Single image deraining is an important and challenging task for some downstream artificial intelligence applications such as video surveillance and self-driving systems. Most of the existing deep-learning-based methods constrain the network to generate derained images but few of them explore feature…
"Visible-infrared person re-identification (VI-ReID) has been a key enabler for night intelligent monitoring system. However, the extensive laboring efforts significantly limit its applications. In this paper, we raise a new label-efficient training pipeline for VI-ReID. Our observation is: RGB ReID…
Learning with limited labeled data is a long-standing problem. Among various solutions, episodic training progres-sively classifies a series of few-shot tasks and thereby is as-sumed to be beneficial for improving the model’s generalization ability. However, recent studies show that it is eveninferi…
Transfer learning eases the burden of training a well-performed model from scratch, especially when training data is scarce and computation power is limited. In deep learning, a typical strategy for transfer learning is to freeze the early layers of a pre-trained model and fine-tune the rest of its…
Rainy images degrade the visional performance that may bring down the accuracy of various applications. In this paper, we propose a novel densely connected network with Dense Feature Pyramid Grids Modules, called DFPGN, to solve the rain removal task. Specifically, in the proposed DFPG, there are fi…
Hole drilling and bolt screwing are frequently performed tasks in construction, decoration, and maintenance. Traditionally, sending human workers to perform these tasks in hard-to-reach locations is both dangerous and costly. In this letter, we present an aerial manipulation platform that allows a h
The automatic generation of long and coherent medical reports given medical images (e.g. Chest X-ray and Fundus Fluorescein Angiography (FFA)) has great potential to support clinical practice. Researchers have explored advanced methods from computer vision and natural language processing to incorpor…
In recent years, single image dehazing deep models based on Atmospheric Scattering Model (ASM) have achieved remarkable results. But the dehazing outputs of those models suffer from color shift. Analyzing the ASM model shows that the atmospheric light factor (ALF) is set as a scalar which indicates…
The data loss caused by unreliable network seriously impacts the results of remote visual SLAM systems. From our experiment, a loss of less than 1 second of data can cause a visual SLAM algorithm to lose tracking. We present a novel buffering method, ORBBuf, to reduce the impact of data loss on remo…
With the large multimedia content online, deep hashing has become a popular method for efficient image retrieval and storage. However, by inheriting the algorithmic backend from softmax classification, these techniques are vulnerable to the well-known adversarial examples as well. The massive collec…
With the rapid growth of visual content, deep learning to hash is gaining popularity in the image retrieval community recently. Although it greatly facilitates search efficiency, privacy is also at risks when images on the web are retrieved at a large scale and exploited as a rich mine of personal i…
Advanced motor skills are essential for robots to physically coexist with humans. Much research on robot dynamics and control has achieved success on hyper robot motor capabilities, but mostly through heavily case-specific engineering. Meanwhile, in terms of robot acquiring skills in a ubiquitous ma…
Image denoising via machine learning techniques, particularly neural networks, has been shown to achieve state-of-the-art performance. However, in practice security and privacy issues undesirably arise in applying a trained machine learning model to image denoising. In this paper, we propose a syste…
Most industrial robots are actuated using geared motors with no direct load side measurement. The flexibility introduced by the gear reducer causes transmission errors and vibrations, which limits the adoption of robot manipulators in many demanding applications. This paper presents a lean and effic