37 accepted papers
Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to protect sensitive data during the training of machine learning models, but its privacy guarantee often comes at a large cost of model performance due to the lack of tight theoretical bounds quantifying privacy loss. While r
The challenge of coalition formation games lies in efficiently navigating the exponentially large space of possible coalitions to identify the optimal partition. While existing approaches to solve coalition formation games either provide optimal solutions with limited scalability or approximate solu…
Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an agent to follow language instructions to reach a target in unseen, 3D environments. A powerful VLN-CE agent requires two crucial abilities during cross-modal planning: spatial reasoning to explore towards the target locat
Diffusion policy sampling enables reinforcement learning (RL) to represent multimodal action distributions beyond suboptimal unimodal Gaussian policies. However, existing diffusion-based RL methods primarily focus on offline setting for reward maximization, with limited consideration of safety in on…
Exogenous MDPs (Exo-MDPs) capture sequential decision-making where uncertainty comes solely from exogenous inputs that evolve independently of the learner’s actions. This structure is especially common in operations research applications such as inventory control, energy storage, and resource alloca…
Recent advances in large language model (LLM) reasoning have shown that reasoning ability can emerge through reinforcement learning (RL). However, despite these successes, RL in its current form remains insufficient to induce capabilities that exceed the limitations of the base model, as it is prima…
Automated interpretation of medical images demands robust modeling of complex visual-semantic relationships while addressing annotation scarcity, label imbalance, and clinical plausibility constraints. We introduce MIRNet (Medical Image Reasoner Network), a novel framework that integrates self-super
Since next-scale prediction was introduced as a new paradigm for autoregressive image generation, it has attracted extensive research interest. By progressively increasing resolution in a draft-to-refinement process, next-scale prediction demonstrates great potential in both generation quality and e
Subject-driven image generation has advanced from single- to multi-subject composition, while neglecting distinction, the ability to distinguish and generate the correct subject when inputs contain multiple candidates. This limitation restricts effectiveness in complex, realistic visual settings. We
Recent advances in video generation have been remarkable, enabling models to produce visually compelling videos with synchronized audio. While existing video generation benchmarks provide comprehensive metrics for visual quality, they lack convincing evaluations for audio-video generation, especiall
While Multimodal Large Language Models (MLLMs) excel on benchmarks, their processing paradigm differs from the human ability to integrate visual information. Unlike humans who naturally bridge details and high-level concepts, models tend to treat these elements in isolation. Prevailing evaluation pr
Differentially private wireless federated learning (DPWFL) is a promising framework for protecting sensitive user data. However, foundational questions on how to precisely characterize privacy loss remain open, and existing work is further limited by convergence analyses that rely on restrictive con…
Automatic audio captioning is essential for audio understanding, enabling applications such as accessibility and content indexing. However, evaluating the quality of audio captions remains a major challenge, especially in reference-free settings where high-quality ground-truth captions are unavailab…
The adeptness of Large Language Models (LLMs) in comprehending and following natural language instructions is critical for their deployment in sophisticated real-world applications. Existing evaluations mainly focus on fragmented constraints or narrow scenarios, but they overlook the comprehensivene…
Large‑scale networked systems, such as traffic, power, and wireless grids, challenge reinforcement‑learning agents with both scale and environment shifts. To address these challenges, we propose \texttt{GSAC} (\textbf{G}eneralizable and \textbf{S}calable \textbf{A}ctor‑\textbf{C}ritic), a framework…
Large Language Models (LLMs) have exhibited significant potential in performing diverse tasks, including the ability to call functions or use external tools to enhance their performance. While current research on function calling by LLMs primarily focuses on single-turn interactions, this paper addr…
According to the Test-Time Scaling, the integration of External Slow-Thinking with the Verify mechanism has been demonstrated to enhance multi-round reasoning in large language models (LLMs). However, in the multimodal (MM) domain, there is still a lack of a strong MM-Verifier. In this paper, we int…
Security concerns related to Large Language Models (LLMs) have been extensively explored; however, the safety implications for Multimodal Large Language Models (MLLMs), particularly in medical contexts (MedMLLMs), remain inadequately addressed. This paper investigates the security vulnerabilities of…
Modern QA systems entail retrieval-augmented generation (RAG) for accurate and trustworthy responses. However, the inherent gap between user queries and relevant documents hinders precise matching. We introduce QAEncoder, a training-free approach to bridge this gap. Specifically, QAEncoder estimates…
Robots rely heavily on visual perception to understand and interact with complex environments. To support this capability, modern perception models have become increasingly large and powerful, resulting in high computational costs that hinder their real-time performance in robotic applications. Exis
In recent years, with the rapid development of Advanced Driver Assistance Systems (ADAS), the demand for the precise and efficient surround view stitching system has significantly increased. Traditional stitching methods perform well in small single-unit vehicles with stable camera poses. However, t
Personalized models have demonstrated remarkable success in understanding and generating concepts provided by users. However, existing methods use separate concept tokens for understanding and generation, treating these tasks in isolation. This may result in limitations for generating images with co…
In recent years, 3D surround view systems have attracted a lot of attention in the field of advanced driver assistance systems (ADAS). However, the foundational assumption of unchanging camera poses in traditional 3D surround view systems, which is designed for single-unit vehicles, results in a fai…
Vision-based Tactile Sensors (VBTSs) show significant promise in that they can leverage image measurements to provide high-spatial-resolution human-like performance. However, current VBTS designs, typically confined to the fingertips of robotic grippers, prove somewhat inadequate, as many grasping a
We study finite episodic Markov decision processes incorporating dynamic risk measures to capture risk sensitivity. To this end, we present two model-based algorithms applied to \emph{Lipschitz} dynamic risk measures, a wide range of risk measures that subsumes spectral risk measure, optimized certa…
This paper investigates the problem of robust beamforming design for dual-function radar-communication (DFRC) systems in complex environments where there exist multiple targets, signal-dependent interferences, imperfect knowledge of the interferences and communication channel state information (CSI)…
Recently, Bird’s Eye View (BEV) detection methodologies that utilize surround-view cameras have seen significant advancements in autonomous driving systems. Traditional methods, however, are constrained by their reliance on specific camera parameters, which poses challenges in generalizing across di…
We present a distribution optimization framework that significantly improves confidence bounds for various risk measures compared to previous methods. Our framework encompasses popular risk measures such as the entropic risk measure, conditional value at risk (CVaR), spectral risk measure, distortio…
We propose an experimental method for measuring bias in face recognition systems. Existing methods to measure bias depend on benchmark datasets that are collected in the wild and annotated for protected (e.g., race, gender) and non-protected (e.g., pose, lighting) attributes. Such observational data…
Inspired by the powerful ability to capture long-distance dependencies in the vision transformer, we propose a novel high-frequency transformer network based on window cross-attention to fuse panchromatic (PAN) and multispectral (MS) images for a high-resolution MS image. To overcome the problem bro…
Automotive surround-view camera systems have been commonly employed in automated driving to aid in near-field sensing and other perception tasks. Due to the large size of the body and the presence of multiple blind spots, panoramic surround-view systems are particularly crucial for tractor-trailer v…
Variational nonlinear chirp mode decomposition (VNCMD) is a recently introduced method for nonlinear chirp signal decomposition that has aroused notable attention in various fields. One limiting aspect of the method is that its performance relies heavily on the setting of the bandwidth parameter. To…
Fisheye object detection is a difficult task in robotics and autonomous driving. One of the reasons is that the fisheye datasets are inferior to standard image datasets in scale and quantity, which inspires the idea of using standard image datasets for fisheye object detection. However, the models t…
We study the problem of learning generative adversarial networks (GANs) for a rare class of an unlabeled dataset subject to a labeling budget. This problem is motivated from practical applications in domains including security (e.g., synthesizing packets for DNS amplification attacks), systems and n…
Recent researches have made remarkable achievements in fast video style transfer based on western paintings. However, due to the inherent different drawing techniques and aesthetic expressions of Chinese ink wash painting, existing methods either achieve poor temporal consistency or fail to transfer…
Distributed stochastic gradient descent (SGD) is essential for scaling the machine learning algorithms to a large number of computing nodes. However, the infrastructures variability such as high communication delay or random node slowdown greatly impedes the performance of distributed SGD algorithm,…
In federated learning, heterogeneity in the clients' local datasets and computation speeds results in large variations in the number of local updates performed by each client in each communication round. Naive weighted aggregation of such models causes objective inconsistency, that is, the global mo…