55 accepted papers
LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon attacks that exploit multi-turn user–agent–environment interactions to achieve objectives infeasible in single-turn settings. To measure agent vul…
Detecting Alzheimer’s disease (AD) from narrative transcripts challenges large language models (LLMs): pre-training rarely covers this out-of-distribution task, and all transcript demos describe the same scene, producing highly homogeneous contexts. These factors cripple both the model’s built-in ta
This paper proposes a modular variable configuration rehabilitation robot (MVCRR), aiming to meet the needs of multi-functional, full-cycle rehabilitation. MVCRR integrates a lower-limb training module and a-sit-to-stand module, offering 16 actuated degrees of freedom and supporting four rehabilitat
This paper presents a rolling-contact joint embedded with a capacitive angle sensing method fabricated using a flexible printed circuit board process. By leveraging the inherent mechanical constraints of the joint's crossed-band structure, enabling high-precision angular measurement without requirin
Large vision-language models (VLMs) are highly vulnerable to multimodal jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails. In this paper, we present DTR, a novel inference-time defense that mitigates multimodal jailbreak attacks through optimizing the model's key
Medical Large Vision-Language Models (Med-LVLMs) have shown promising results in clinical applications, but often suffer from hallucinated outputs due to misaligned visual understanding. In this work, we identify two fundamental limitations contributing to this issue: insufficient visual representat
Large language models (LLMs) increasingly perform multi-step reasoning, where intermediate claims form implicit directed acyclic graphs whose node correctness is structurally conditioned on their ancestors. This makes factuality uncertainty structural, rather than a trivial accumulation of node-wise…
Constructing historical language models (LMs) plays a crucial role in aiding archaeological provenance studies and understanding ancient cultures. However, existing resources present major challenges for training effective LMs on historical texts. First, the scarcity of historical language samples r
Adversarial training is an effective technique for enhancing the robustness of deep neural networks (DNNs). Prior research shows that misclassified examples influence final adversarial robustness much more than correctly classified examples. Ignoring this difference during training can hurt model pe
Complex tables with multi-level headers, merged cells and heterogeneous layouts pose persistent challenges for large language models (LLMs) in both understanding and reasoning. Existing approaches typically rely on table linearization or normalized grid modeling. However, these representations strug…
Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing images based on free-form natural language expressions. Existing approaches are typically constrained to closed-set vocabularies, limiting their applicability in open-world scenarios. While recent attempts to leverage
Large reasoning models (LRMs) exhibit unprecedented capabilities in solving complex problems through Chain-of-Thought (CoT) reasoning. However, recent studies reveal that their final answers often contradict their own reasoning traces. We hypothesize that this inconsistency stems from two competing…
Harmful fine-tuning attacks represent a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment, they fail to address models' inherent `trainability' on ha…
While multimodal large language models (MLLMs) have achieved remarkable success in recent advancements, their susceptibility to jailbreak attacks has come to light. In such attacks, adversaries exploit carefully crafted prompts to coerce models into generating harmful or undesirable content. Existin
LiDAR-based SLAM is an essential technology for autonomous robots, benefited from its high accuracy and scale invariance. Interestingly, researchers have been increasingly focusing on establishing simple, efficient, but effective LiDAR SLAM systems recently. In this paper, we propose a novel and com
Graph Neural Networks (GNNs) has been widely used in a variety of fields because of their great potential in representing graph-structured data. However, lacking of rigorous uncertainty estimations limits their application in high-stakes. Conformal Prediction (CP) can produce statistically guarantee…
Place recognition is an important component for autonomous robot navigation. Many existing LiDAR-based place recognition methods encode the structural information of 3D LiDAR data into 2D image representations. However, most of these intermediates only exploit the projection in a single view, ignori
Open-domain timeline summarization (TLS) faces challenges from information overload and data sparsity when processing large-scale textual streams. Existing methods struggle to capture coherent event narratives due to fragmented descriptions and often accumulate noise through iterative retrieval stra
Differentially private diffusion models (DPDMs) harness the remarkable generative capabilities of diffusion models while enforcing differential privacy (DP) for sensitive data. However, existing DPDM training approaches often suffer from significant utility loss, large memory footprint, and expensiv…
Jailbreak attacks circumvent LLMs' built-in safeguards by concealing harmful queries within adversarial prompts. While most existing defenses attempt to mitigate the effects of adversarial prompts, they often prove inadequate as adversarial prompts can take arbitrary, adaptive forms. This paper intr…
Inspired by how humans perceive, remember, and understand the world, semantic graphs have become an efficient solution for place representation and location. However, many current graph-based LiDAR loop closing methods focus on extracting adjacency matrices or semantic histograms to describe the sce
This paper delves into a novel backdoor attack scenario, aiming to uncover potential security risks associated with Multimodal Large Language Models (MLLMs) during multi-round open-ended conversations with users. In the practical use of MLLMs, users have full control over the interaction process wit…
Recent advancements in unique acoustic sensing devices and large-scale audio recognition models have unlocked new possibilities for environmental sound monitoring and detection. However, applying pretrained models to non-conventional acoustic sensors results in performance degradation due to domain…
Various watermarking methods (“watermarkers”) have been proposed to identify LLM-generated texts; yet, due to the lack of unified evaluation platforms, many critical questions remain under-explored: i) What are the strengths/limitations of various watermarkers, especially their attack robustness? ii
In robot-assisted retinal surgery, a Remote Center of Motion (Rcm) allows the surgical instrument to rotate around a distal fixed point without any lateral translations. The Rcm point should be perfectly aligned inside the trocar. Otherwise, unexpected tool translations at the expected remote center…
Parameter Efficient Fine-Tuning (PEFT) offers an efficient solution for fine-tuning large pretrained language models for downstream tasks. However, most PEFT strategies are manually designed, often resulting in suboptimal performance. Recent automatic PEFT approaches aim to address this but face cha…
Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor could be misled to embed backdoored data close to an attack targ…
The Vision-and-Language Navigation in Continuous Environments (VLN-CE) task requires an agent to follow a language instruction in a realistic environment. Understanding the environment is crucial, yet current methods are relatively simple and direct, without delving into the interplay between langua…
Backdoor attacks have been shown to be a serious security threat against deep learning models, and various defenses have been proposed to detect whether a model is backdoored or not. However, as indicated by a recent black-box attack, existing defenses can be easily bypassed by implanting the backdo…
Pre-trained language models (PLMs) have attracted enormous attention over the past few years with their unparalleled performances. Meanwhile, the soaring cost to train PLMs as well as their amazing generalizability have jointly contributed to few-shot fine-tuning and prompting as the most popular tr…
We present ReMasker, a new method of imputing missing values in tabular data by extending the masked autoencoding framework. Compared with prior work, ReMasker is extremely simple -- besides the missing values (i.e., naturally masked), we randomly "re-mask" another set of values, optimize the autoen…
Citing comprehensively and appropriately has become a challenging task with the explosive growth of scientific publications. Current citation recommendation systems aim to recommend a list of scientific papers for a given text context or a draft paper. However, none of the existing work focuses on a…
Learning to collaborate has witnessed significant progress in multi-agent reinforcement learning (MARL). However, promoting coordination among agents and enhancing exploration capabilities remain challenges. In multi-agent environments, interactions between agents are limited in specific situations.…
Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the “pre-training & finetuning” learning paradigm significantly improves the VQA performance, the adversarial robustness of such a learning paradigm has not been explored. In this p…
As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels. In addition to eliminating the need for labeled data, research has found that SSL improves the adversarial robustness over supervised l…
Pre-trained language models (PLMs) have demonstrated remarkable performance as few-shot learners. However, their security risks under such settings are largely unexplored. In this work, we conduct a pilot study showing that PLMs as few-shot learners are highly vulnerable to backdoor attacks while ex…
Diffusion-based image generation models, such as Stable Diffusion or DALL·E 2, are able to learn from given images and generate high-quality samples following the guidance from prompts. For instance, they can be used to create artistic images that mimic the style of an artist based on his/her origi…
Having the difficulty of solving the semantic gap between images and texts for the image captioning task, conventional studies in this area paid some attention to treating semantic concepts as a bridge between the two modalities and improved captioning performance accordingly. Although promising res…
Due to repetitive trial-and-error style interactions between agents and a fixed traffic environment during the policy learning, existing Reinforcement Learning (RL)-based Traffic Signal Control (TSC) methods greatly suffer from long RL training time and poor adaptability of RL agents to other comple…
Acute appendicitis (AA) is one of the most prevalent surgical acute abdominal condition diseases. The treatment management of A A is highly dependent on the CT image diagnosis. However, the in-flamed appendix exhibits blurred boundaries with nearby tissue, varying shapes, and sizes. These properties…
Miniature soft robots present great potential in delicate manipulations due to their gentle force, complaint structures, and flexible motions. Easy control and fast response make pneumatic actuation a prevalent method for driving soft robotics. In addition, sequential motions are also crucial for en…
This paper asks the intriguing question: is it possible to exploit neural architecture search (NAS) as a new attack vector to launch previously improbable attacks? Specifically, we present EVAS, a new attack that leverages NAS to find neural architectures with inherent backdoors and exploits such vu…
Recent years have witnessed a surge of certified robust training pipelines against text adversarial perturbation constructed by synonym substitutions. Given a base model, existing pipelines provide prediction certificates either in the discrete word space or the continuous latent space. However, the…
Utility pole detection and localization is the most fundamental application in aerial-optic cables using distributed acoustic sensing (DAS). The existing pole localization method recognizes the hammer knock signal on DAS traces by learning from knocking vibration patterns. However, it requires many…
Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Existing approaches mainly focus on exploring the adversarial robustness under the white-box setting, which is unrealistic. I…
"Backdoor attacks have been shown to be a serious threat against deep learning systems such as biometric authentication and autonomous driving. An effective backdoor attack could enforce the model misbehave under certain predefined conditions, i.e., triggers, but behave normally otherwise. The trigg…
Fine-grained Entity Typing (FET) has made great progress based on distant supervision but still suffers from label noise. Existing FET noise learning methods rely on prediction distributions in an instance-independent manner, which causes the problem of confirmation bias. In this work, we propose a…
Due to the prosperity of Artificial Intelligence (AI) techniques, more and more backdoors are designed by adversaries to attack Deep Neural Networks (DNNs). Although the state-of-the-art method Neural Attention Distillation (NAD) can effectively erase backdoor triggers from DNNs, it still suffers fr…
Multi-Document Scientific Summarization (MDSS) aims to produce coherent and concise summaries for clusters of topic-relevant scientific papers. This task requires precise understanding of paper content and accurate modeling of cross-paper relationships. Knowledge graphs convey compact and interpreta…
This paper focuses on a newly challenging setting in hard-label adversarial attacks on text data by taking the budget information into account. Although existing approaches can successfully generate adversarial examples in the hard-label setting, they follow an ideal assumption that the victim model…
User targeting is an essential task in the modern advertising industry: given a package of ads for a particular category of products (e.g., green tea), identify the online users to whom the ad package should be targeted. A (ad package specific) user targeting model is typically trained using histori…
This paper presents a tightly coupled pipeline, which efficiently fuses measurements of LiDAR, camera, IMU, encoder, and GNSS to estimate the robot state and build a map even in challenging situations. The depth of visual features is extracted by projecting the LiDAR point cloud and ground plane int…
Providing explanations for deep neural networks (DNNs) is essential for their use in domains wherein the interpretability of decisions is a critical prerequisite. Despite the plethora of work on interpreting DNNs, most existing solutions offer interpretability in an ad hoc, one-shot, and static mann…
In recent years, many excellent SLAM methods based on cameras, especially the camera-IMU fusion (VIO), have emerged, which has greatly improved the accuracy and robustness of SLAM. However, we find through experiments that most of the existing VIO methods perform well on drones or drone datasets, bu…
We consider the problem of unknown emitter geolocation using the time difference of arrival (TDOA) of the path rays through the ionosphere by multiple coordinated distant receivers. We formulate the geolocation in the sense of maximum likelihood with the exact ray expressions for the quasi-parabolic…