77 accepted papers
General audio understanding is a fundamental goal for large audio-language models, with audio captioning serving as a cornerstone task for their development. However, progress in this domain is hindered by existing datasets, which lack the scale and descriptive granularity required to train truly ve…
Zero-shot (ZS) 3D anomaly detection is crucial for reliable industrial inspection, as it enables detecting and localizing defects without requiring any target-category training data. Existing approaches render 3D point clouds into 2D images and leverage pre-trained Vision-Language Models (VLMs) for
Computer-using agents (CUAs) enable task completion through natural interaction with operating systems and software interfaces. While script-based verifiers are widely adopted for evaluation, they suffer from limited scalability and inability to provide step-wise assessment. Reward models offer prom…
Test-time scaling improves LLM performance by generating multiple candidate solutions, yet token-level sampling requires temperature tuning that trades off diversity against stability. Fine-grained MoE, featuring hundreds of well-trained experts per layer and multi-expert activation per token, offer…
Low-light object detection faces significant challenges due to the substantial domain shift between normal-light and low-light conditions. Prior works often enhance low-light images before detection, but this preprocessing can introduce artifacts that degrade detection performance since it focuses o
Recent large reasoning models (LRMs) driven by reinforcement learning algorithms (e.g., GRPO) have achieved remarkable performance on challenging reasoning tasks. However, these models suffer from overthinking, generating unnecessarily long and redundant reasoning even for simple questions, which su…
While semi-asynchronous federated learning (SAFL) combines the efficiency of synchronous training with the flexibility of asynchronous updates, it inherently suffers from participation bias, which is further exacerbated by non-IID data distributions. More importantly, hierarchical architecture shift
Federated Learning (FL) often suffers from degraded generalization under statistical heterogeneity, where client updates systematically deviate from the global objective. While recent Sharpness-Aware Minimization (SAM) methods promote locally flat solutions, they implicitly assume that local flatnes…
Federated Learning (FL) enables collaborative model training across decentralized clients, but its performance often degrades under non-IID data distributions, particularly in the presence of data skew. Existing approaches mitigate this issue by estimating client skew via kernel density estimation o…
Recent years have witnessed remarkable progress in multimodal learning within computational pathology. Existing models primarily rely on vision and language modalities; however, language alone lacks molecular specificity and offers limited pathological supervision, leading to representational bottle…
Drone-based building defect segmentation remains challenging due to complex surface textures and illumination variations. We propose TPSegformer, a topology-preserving segmentation framework that mitigates mis-segmentation in such scenarios. Its decoder incorporates a Hilbert curve-based topology-pr
Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing studies stimulate exploration through the lens of policy en…
Medical image segmentation annotation suffers from inter-rater variability (IRV) due to differences in annotators' expertise and the inherent blurriness of medical images. Standard approaches that simply average expert labels are flawed, as they discard the valuable clinical uncertainty revealed in…
While large audio-language models have advanced open-ended audio understanding, they still fall short of nuanced human-level comprehension. This gap persists largely because current benchmarks, limited by data annotations and evaluation metrics, fail to reliably distinguish between generic and highl…
Precise recognition, editing, and generation of molecules are essential prerequisites for both chemists and AI systems tackling various chemical tasks. We present MolLangBench, a comprehensive benchmark designed to evaluate fundamental molecule-language interface tasks: language-prompted molecular s…
Asynchronous Federated Learning (AFL) is acclaimed for accelerating collaborative training on heterogeneous systems by eliminating the wait for stragglers. While current solutions focus on improving convergence amidst update delays, they neglect how delayed aggregation fosters free-riding attacks, a
Large language models (LLMs) are moving beyond static uses and are now powering agents that learn during their interaction with external environments. For example, agents can learn reusable skills while navigating web pages or toggling new tools. However, existing methods for skill learning often cr…
With the increasing application of high-stakes decisionmaking application in Federated Learning (FL), ensuring fairness across different populations to prevent biases against certain groups has become crucial. However, achieving group fairness (GF) in FL presents a formidable challenge due to its de
Topological Data Analysis (TDA) provides artificial intelligence (AI) systems with mathematically rigorous geometric descriptors through Persistent Homology (PH), capturing essential shape characteristics in high-dimensional data. Yet, PH’s combinatorial complexity and sensitivity to outliers hinder
Training web agents to navigate complex, real-world websites requires them to master subtasks—short-horizon interactions on multiple UI components (e.g., choosing the correct date in a date picker, or scrolling in a container to extract information). We introduce WARC-Bench (Web Archive Benchmark),…
Due to control limitations in the denoising process and the lack of training, zero-shot video editing methods often struggle to meet user instructions, resulting in generated videos that are visually unappealing and fail to fully satisfy expectations. To address this problem, we propose Align-A-Vide…
Multi-agent systems must learn to communicate and understand interactions between agents to achieve cooperative goals in partially observed tasks. However, existing approaches lack a dynamic directed communication mechanism and rely on global states, thus diminishing the role of communication in cen…
With the popularity of large language models and their high-quality text generation capabilities, researchers are using them as auxiliary tools for text summary writing. Although summaries generated by these large language models are smooth and capture key information sufficiently, the quality of th…
Online Federated Learning (OFL) is a real-time learning paradigm that sequentially executes parameter aggregation immediately for each random arriving client. To motivate clients to participate in OFL, it is crucial to offer appropriate incentives to offset the training resource consumption. However
The rapid advancement of generative models has led to the widespread emergence of highly realistic synthetic images, making the detection of AI-generated content increasingly critical. In particular, diffusion models have recently achieved unprecedented levels of visual fidelity, further raising con…
The recent success and openness of DeepSeek-R1 have brought widespread attention to Group Relative Policy Optimization (GRPO) as a reinforcement learning method for large reasoning models (LRMs). In this work, we analyze the GRPO objective under a binary reward setting and reveal an inherent limitat…
Self-disclosure can provide psychological comfort and social support, but it also carries the risk of unintentionally revealing sensitive information, leading to serious privacy concerns. Research on self-disclosure in Chinese multimodal contexts remains limited, lacking high-quality corpora, analys
Text-to-image (T2I) generation has made significant advances in recent years, but challenges still remain in the generation of perceptual artifacts, misalignment with complex prompts, and safety. The prevailing approach to address these issues involves collecting human feedback on generated images,…
Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely chain-of-thought (CoT), is expected to universally improve capabi…
Large Language Models (LLMs) have demonstrated strong generative capabilities but remain prone to inconsistencies and hallucinations. We introduce Peer Elicitation Games (PEG), a training-free, game-theoretic framework for aligning LLMs through a peer elicitation mechanism involving a generator and…
Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustworthiness of Med-LVLMs remains unverified, posing s…
Image cartoonization has attracted significant interest in the field of image generation. However, most of the existing image cartoonization techniques require re-training models using images of cartoon style. In this paper, we present CartoonDiff, a novel training-free sampling approach which gener…
Iontronic tactile sensors are promising to measure spatial-temporal contact information with high performance. However, no suitable measuring method has been presented, due to issues with crosstalk and non-negligible equivalent resistance. Hence, this study presents an impedance-separating method, w…
Detecting abrupt changes in data distribution is one of the most significant tasks in streaming data analysis. Although many unsupervised Change-Point Detection (CPD) methods have been proposed recently to identify those changes, they still suffer from missing subtle changes, poor scalability, or/an…
In recent years, deep learning methods have shown promising results in Single Image Deraining (SID). However, these methods still suffer from unsatisfactory residual rain streaks, primarily due to the absence of image priors embedding and limitations in modeling capacity. In this paper, we propose a…
We explore the boundaries of scaling up a multilingual vision and language model both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks including multiple image-based captioning an…
"Recent works have demonstrated that using reinforcement learning (RL) with multiple quality rewards can improve the quality of generated images in text-to-image (T2I) generation. However, manually adjusting reward weights poses challenges and may cause over-optimization in certain metrics. To solve…
Developing intelligent pediatric consultation systems offers promising prospects for improving diagnostic efficiency, especially in China, where healthcare resources are scarce. Despite recent advances in Large Language Models (LLMs) for Chinese medicine, their performance is sub-optimal in pediatri…
The recent emergence of Medical Large Vision Language Models (Med-LVLMs) has enhanced medical diagnosis. However, current Med-LVLMs frequently encounter factual issues, often generating responses that do not align with established medical facts. Retrieval-Augmented Generation (RAG), which utilizes e…
Marine radar is employed across multiple fields, notably in navigation, meteorology, defense, and security. Marine radar images are highly sensitive to sea clutter, highlighting the crucial importance of sea clutter suppression in radar image processing. However, existing algorithms for sea clutter…
Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However many generated images still suffer from issues such as artifacts/implausibility misalignment with text descriptions…
Detection of face forgery videos remains a formidable challenge in the field of digital forensics, especially the generalization to unseen datasets and common perturbations. In this paper, we tackle this issue by leveraging the synergy between audio and visual speech elements, embarking on a novel a…
Point cloud filtering is a fundamental 3D vision task which aims to remove noise while recovering the underlying clean surfaces. State-of-the-art methods remove noise by moving noisy points along stochastic trajectories to the clean surfaces. These methods often require regularization within the tra…
With the popularity of large language models (LLMs) and their ability to handle longer input documents, there is a growing need for high-quality long document summarization datasets. Although many models already support 16k input, current lengths of summarization datasets are inadequate, and salient…
Progress in human behavior modeling involves understanding both implicit, early-stage perceptual behavior, such as human attention, and explicit, later-stage behavior, such as subjective preferences or likes. Yet most prior research has focused on modeling implicit and explicit human behavior in iso…
As graph data size increases, the vast latency and memory consumption during inference pose a significant challenge to the real-world deployment of Graph Neural Networks (GNNs). While quantization is a powerful approach to reducing GNNs complexity, most previous works on GNNs quantization fail to ex…
Large language models (LLMs) have shown increasing capacity at planning and executing a high-level goal in a live computer environment (e.g. MiniWoB++). To perform a task, recent works often require a model to learn from trace examples of the task via either supervised learning or few/many-shot prom…
As deep learning gains popularity in modelling dynamical systems, we expose an underappreciated misunderstanding relevant to modelling dynamics on networks. Strongly influenced by graph neural networks, latent vertex embeddings are naturally adopted in many neural dynamical network models. However,…
Since the introduction of distantly supervised relation extraction methods, numerous approaches have been developed, the most representative of which is multi-instance learning (MIL). To find reliable features that are most representative of multi-instance bags, aggregation strategies such as AVG (a…
The quality of point clouds is often limited by noise introduced during their capture process. Consequently, a fundamental 3D vision task is the removal of noise, known as point cloud filtering or denoising. State-of-the-art learning based methods focus on training neural networks to infer filtered…
This paper seeks to address a gap in optimizing Average Precision (AP) while ensuring adversarial robustness, an area that has not been extensively explored to the best of our knowledge. AP maximization for deep learning has widespread applications, particularly when there is a significant imbalance…
Layout design is an important task in various design fields, including user interfaces, document, and graphic design. As this task requires tedious manual effort by designers, prior works have attempted to automate this process using generative models, but commonly fell short of providing intuitive…
Mobile UI understanding is important for enabling various interaction tasks such as UI automation and accessibility. Previous mobile UI modeling often depends on the view hierarchy information of a screen, which directly provides the structural data of the UI, with the hope to bypass challenging tas…
The geometrical theory of diffraction (GTD) has been widely investigated to describe the target scattering behaviors with the low-frequency ultra-wideband (LFW) radar. In this paper, we propose a new model-based deep learning method for GTD parameter estimation. The proposed method is designed by un…
For strong maneuvering targets, the drastic change of target motion models makes the tracking methods hard to adapt and provide accurate state estimation promptly. To solve the state estimation problem of strong maneuvering targets, we propose a transformer-based tracking network, named TrTNet. The…
The Mean-Teacher (MT) scheme is widely adopted in semi-supervised object detection (SSOD). In MT, sparse pseudo labels, offered by the final predictions of the teacher (e.g., after Non Maximum Suppression (NMS) post-processing), are adopted for the dense supervision for the student via hand-crafted…
Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression and acceleration. Compared with image classification, object detection is a more complex task, and designing specific KD m…
Variance reduction techniques such as SPIDER/SARAH/STORM have been extensively studied to improve the convergence rates of stochastic non-convex optimization, which usually maintain and update a sequence of estimators for a single function across iterations. What if we need to track multiple functi…
"Recently low-precision deep learning accelerators (DLAs) have become popular due to their advantages in chip area and energy consumption, yet the low-precision quantized models on these DLAs bring in severe accuracy degradation. One way to achieve both high accuracy and efficient inference is to de…
"In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques currently neglect some important properties of object detection, hindering efficient learning on unlabeled data. Specific…
Recently, significant progress has been made in masked image modeling to catch up to masked language modeling. However, unlike words in NLP, the lack of semantic decomposition of images still makes masked autoencoding (MAE) different between vision and language. In this paper, we explore a potential…
In this paper, we propose systematic and efficient gradient-based methods for both one-way and two-way partial AUC (pAUC) maximization that are applicable to deep learning. We propose new formulations of pAUC surrogate objectives by using the distributionally robust optimization (DRO) to define the…
Retinal surgeons are required to manipulate multiple surgical instruments in a confined intraocular space, while the instruments are constrained at the small incisions made on the sclera. Furthermore, physiological hand tremor can affect the precision of the instrument motion. The Steady-Hand Eye Ro
In dynamic neural networks that adapt computations to different inputs, gating-based methods have demonstrated notable generality and applicability in trading-off the model complexity and accuracy. However, existing works only explore the redundancy from a single point of the network, limiting the p…
Sinkhorn divergence has become a very popular metric to compare probability distributions in optimal transport. However, most works resort to Sinkhorn divergence in Euclidean space, which greatly blocks their applications in complex data with nonlinear structure. It is therefore of theoretical deman…
Attentional mechanisms are order-invariant. Positional encoding is a crucial component to allow attention-based deep model architectures such as Transformer to address sequences or images where the position of information matters. In this paper, we propose a novel positional encoding method based on…
Lumbar injection is an image-guided procedure performed manually for diagnosis and treatment of lower back pain and leg pain. Previously, we have developed and verified an MR-Conditional robotic solution to assisting the needle insertion process. Drawing on our clinical experiences, a virtual remote…
This paper reports the development of a fully actuated body-mounted robotic assistant for MRI-guided low back pain injection. The robot is designed with a 4-DOF needle alignment module and a 2-DOF remotely actuated needle driver module. The 6-DOF fully actuated robot can operate inside the scanner b…
Robot-assisted vitreoretinal surgery can filter surgeons' hand tremors and provide safe, accurate tool manipulation. In this paper, we report the design, optimization, and evaluation of a novel tilt mechanism for a new Steady-Hand Eye Robot (SHER). The new tilt mechanism features a four-bar linkage…
In this paper, we present a new detector for the detection of sparse stochastic signals using 1-bit data in two-level two- degree tree-structured sensor networks (2L-2D TSNs). Related prior work mostly concentrates on parallel sensor networks (PSNs). However, PSNs may sometime become impractical in…
This paper reports the improved design, system integration, and initial experimental evaluation of a fully actuated body-mounted robotic system for real-time MRI-guided lower back pain injections. The 6-DOF robot is composed of a 4-DOF needle alignment module and a 2-DOF remotely actuated needle dri
A mirrored array configuration, which consists of an ordinary linear array and a reflector, is proposed. The mirrored arrays can provide composable degrees of freedom (DOF) for array processing by combined measurements with the help of mechanical adjustment (e.g., movement or rotation). This composa…
Persistence diagram (PD) has been considered as a compact descriptor for topological data analysis (TDA). Unfortunately, PD cannot be directly used in machine learning methods since it is a multiset of points. Recent efforts have been devoted to transforming PDs into vectors to accommodate machine l…
Recently binary weight networks have attracted lots of attentions due to their high computational efficiency and small parameter size. Yet they still suffer from large accuracy drops because of their limited representation capacity. In this paper, we propose a novel semi-binary decomposition method…
This paper deals with designing incoherent sparsifying dictionaries. A new framework is proposed, in which the sparse representation error and mutual coherence are embedded. An alternating minimization method is developed for solving the optimal dictionary problem. One of the significant features of…
Based on the orthogonality between the signal subspace and the noise subspace, we propose a sparse recovery method for the direction of arrival (DOA) estimation. With the assumption of uncorrelated sources, signal covariance matrix fitting is achieved by embedding the MUSIC-like weights into a quadr…
In this paper, we consider the problem of fusion of multi-polarization radar images and develop a new greedy algorithm referred to as hybrid matching pursuit (HMP). By combining the strengths of the orthogonal matching pursuit algorithm and the subspace pursuit algorithm, HMP can enhance target refl…