47 accepted papers
Large Language Model (LLM) agents are increasingly deployed in practice across a wide range of autonomous applications. Yet current safety mechanisms for LLM agents focus almost exclusively on preventing failures in advance, providing limited capabilities for responding to, containing, or recovering…
Multimodal learning, while contributing to numerous success stories across various fields, faces the challenge of prohibitively expensive manual annotation. To address the scarcity of annotated data, a popular solution is unsupervised domain adaptation, which has been extensively studied in unimodal
Large language models (LLMs) can exhibit *concept-conditioned semantic divergence*: common high-level cues (e.g., ideologies, public figures) elicit unusually uniform, stance-like responses that evade token-trigger audits. This behavior falls in a blind spot of current safety evaluations, yet carrie…
Sharpness (of the loss minima) is widely believed to be a good indicator of generalization of neural networks. Unfortunately, the correlation between existing sharpness measures and the generalization is not that strong as expected, sometimes even contradiction occurs. To address this problem, a key…
Vision-Language Models (VLMs) extend Large Language Models (LLMs) with visual perception capabilities, unlocking broad applications across many domains. However, ensuring their safety remains a critical challenge, as adversarial visual inputs can easily bypass built-in safeguards and elicit harmful
The recent success of machine learning models, especially large-scale classifiers and language models, relies heavily on training with massive data. These data are often collected from online sources. This raises serious concerns about the protection of user data, as individuals may not have given c
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the root causes of these failures poses a critical challenge for AI…
Multimodal learning has celebrated remarkable success across diverse areas, yet faces the challenge of prohibitively expensive data collection and annotation when adapting models to new environments. In this context, domain adaptation has gained growing popularity as a technique for knowledge transf…
Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce adversary-specified outputs. While prior research has predominantly fo…
Large Language Models (LLMs) are vulnerable to backdoor attacks that manipulate outputs via hidden triggers. Existing defense methods—designed for vision/text classification tasks—fail for text generation. We propose *Internal Consistency Regularization (CROW)*, a defense leveraging the observation…
Motion planning is a difficult task, especially when generating feasible future trajectories in complex and interactive scenarios. While recent advancements in imitation-based planning have shown significant progress, this approach often encounters causal confusion in dynamic traffic environments. T
Despite their advances and success, real-world deep neural networks are known to be vulnerable to adversarial attacks. Universal adversarial perturbation, an input-agnostic attack, poses a serious threat for them to be deployed in security-sensitive systems. In this case, a single universal adversar…
Influence functions are important for quantifying the impact of individual training data points on a model’s predictions. Although extensive research has been conducted on influence functions in traditional machine learning models, their application to large language models (LLMs) has been limited.
Trustworthy multi-modal learning integrates multiple sources of data reliably. However, the current methods still focus on performance improvement by developing deep multi-modal networks. These approaches frequently encounter challenges due to the inherent non-convex nature of deep neural networks a…
In Versatile Video Coding (VVC), Rate-Distortion Optimized Quantization (RDOQ) is a widely adopted technique to strike a balance between bit rate and distortion. However, the computational complexity introduced by RDOQ poses significant challenges for real-time applications. To address this issue, w…
We address the problem of object placement with user instructions using LLM and diffusion model. Traditional methods struggle to find a suitable location for filling the object with a semantically reasonable size. In this work, we leverage the LLM to predict the coordinates of the added object with…
Large language models (LLMs) typically provide multilingual support and demonstrate remarkable capabilities in solving tasks described in different languages. However, LLMs can exhibit linguistic discrimination due to the uneven distribution of training data across languages. That is, LLMs struggle
Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful and harmful responses poses significant risks, particularly in critical applications. This highlights the urgent need for systematic methods to detect and prevent such misbehavior. While…
Video streaming services typically employ traditional codecs, such as H.264, to encode videos into multiple bitrate representations. These codecs are tightly limited by discrete quantization parameters (QPs), resulting in encoded rates that do not align with the target bitrate. Additionally, the sub…
Large Language Models (LLMs) have emerged as a transformative AI paradigm, profoundly influencing broad aspects of daily life. Despite their remarkable performance, LLMs exhibit a fundamental limitation: hallucination—the tendency to produce misleading outputs that appear plausible. This inherent…
The interpretability of deep black-box temporal models is crucial in modern machine learning. Identifying crucial time steps and temporal patterns is an important way in understanding how a black-box model makes a decision on a time series instance. Saliency methods are widely used for the interpret…
Emotional reasoning is essential for improving human-AI interactions, particularly in mental health support and empathetic systems. However, current approaches, which primarily map sensory inputs to fixed emotion labels, fail to understand the intricate relationships between motivations, thoughts, a
Formal verification provides critical security assurances for neural networks, yet its practical application suffers from the long verification time. This work introduces a novel method for training verification-friendly neural networks, which are robust, easy to verify, and relatively accurate. Our…
Deep learning models often suffer from performance degradation in unseen domains, posing a risk for safety-critical applications such as autonomous driving. To tackle this problem, recent studies have leveraged pre-trained Visual Foundation Models (VFMs) to enhance generalization. However, exsiting…
Large Vision-Language Models (LVLMs) have made significant strides in multimodal comprehension, thanks to extensive pre-training and fine-tuning on large-scale visual datasets. However, despite their robust textual safety mechanisms, they remain vulnerable to harmful visual inputs. Existing safeguar
Large Language Models (LLMs) can elicit unintended and even harmful content when misaligned with human values, posing severe risks to users and society. To mitigate these risks, current evaluation benchmarks predominantly employ expert-designed contextual scenarios to assess how well LLMs align with…
Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to interpret their behaviors through the lens of inner representation. However, develo…
This paper investigates unsupervised multimodal domain adaptation for multimodal emotion recognition, which is a solution for data scarcity yet remains under studied. Due to the varying distribution discrepancies of different modalities between source and target domains, the primary challenge lies i…
In this paper, a power optimization (PO) strategy is proposed to combat deception jamming in multi-radar systems (MRSs) performing multi-target tracking (MTT). As a crucial parameter for distinguishing between physical and false targets in MRS under deception jamming, we propose integrating the dece…
Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts even when aligned via Reinforcement Learning from Human Feedbac…
Emotion Recognition in conversations (ERC) involves an internal cognitive process that interprets emotional cues by using a collection of past emotional experiences. However, many existing methods struggle to decipher emotional cues in dialogues since they are insufficient in understanding the rich…
Network pruning is a commonly used measure to alleviate the storage and computational burden of deep neural networks. However, the fundamental limit of network pruning is still lacking. To close the gap, in this work we'll take a first-principles approach, i.e. we'll directly impose the sparsity con…
Text-guided image manipulation has attracted significant attention recently. Prevailing techniques concentrate on image attribute editing for individual objects, however, encountering challenges when it comes to multi-object editing. The main reason is the lack of consistency constraints on the spat…
Multimodal learning is susceptible to modality missing, which poses a major obstacle for its practical applications and, thus, invigorates increasing research interest. In this paper, we investigate two challenging problems: 1) when modality missing exists in the training data, how to exploit the in…
AI-enabled collaborative robots are designed to be used in close collaboration with humans, thus requiring stringent safety standards and quick response times. Adversarial attacks pose a significant threat to the deep learning models of these systems, making it crucial to develop methods to improve
Most anomaly detection (AD) models are learned using only normal samples in an unsupervised way, which may result in ambiguous decision boundary and insufficient discriminability. In fact, a few anomaly samples are often available in real-world applications, the valuable knowledge of known anomalies…
Multi-modal emotion recognition has gained increasing attention in recent years due to its widespread applications and the advances in multi-modal learning approaches. However, previous studies primarily focus on developing models that exploit the unification of multiple modalities. In this paper, w…
One of the most challenges for anomaly detection (AD) is how to learn one unified and generalizable model to adapt to multi-class especially cross-class settings: the model is trained with normal samples from seen classes with the objective to detect anomalies from both seen and unseen classes. In t…
Existing unsupervised domain adaptation (UDA) studies focus on transferring knowledge in an offline manner. However, many tasks involve online requirements, especially in real-time systems. In this paper, we discuss Online UDA (OUDA) which assumes that the target samples are arriving sequentially as…
We present a novel no-reference quality assessment metric, the image transferred point cloud quality assessment (IT-PCQA), for 3D point clouds. For quality assessment, deep neural network (DNN) has shown compelling performance on no-reference metric design. However, the most challenging issue for no…
Collaborative Robots (cobots) are regarded as highly safety-critical cyber-physical systems (CPSs) owing to their close physical interactions with humans. In settings such as smart factories, they are frequently augmented with AI. For example, in order to move materials, cobots utilize object detect
Autonomous vehicles (AVs) play an important role in transforming our transportation systems and relieving traffic congestion. To guarantee their safety, AVs must be sufficiently tested before they are deployed to public roads. Existing testing often focuses on AVs’ collision avoidance on a given rou…
Motivated by the emerging use of multi-agent reinforcement learning (MARL) in engineering applications such as networked robotics, swarming drones, and sensor networks, we investigate the policy evaluation problem in a fully decentralized setting, using temporal-difference (TD) learning with linear…
Pedestrian detection benefits greatly from deep convolutional neural networks (CNNs). However, it is inherently hard for CNNs to handle situations in the presence of occlusion and scale variation. In this paper, we propose W^3Net, which attempts to address above challenges by decomposing the pedestr…
The present paper develops a novel aggregated gradient approach for distributed machine learning that adaptively compresses the gradient communication. The key idea is to first quantize the computed gradients, and then skip less informative quantized gradient communications by reusing outdated gradi…
In this paper, we propose unsupervised person re-identification (ReID) using reliable and soft labels. We provide unsupervised person ReID to consider unknown pedestrian queries. We update ResNet model for person ReID based on reliable and soft labels. First, we perform unsupervised clustering on pe…
Due to the quality of paper and long-time preservation, the ink on one side of the historical documents often seeps through and appears on the other side. In this paper, a new blind ink bleed-through removal method is proposed to deal with the scanned historical document images. The scanned historic…