29 accepted papers
The automated design of agentic systems offers a promising pathway for scaling large language models (LLMs) beyond single-agent reasoning. While prior work has advanced task performance through handcrafted or automatically generated multi-agent workflows, robustness is often treated as an afterthoug…
Multivariate time series (MTS) classification is foundational to pervasive computing and financial analysis, yet existing multi-scale paradigms are often constrained by suboptimal representation fidelity. We identify two critical bottlenecks: temporal non-causality in standard encoders that induces
To address the limitations of Transformer decoders in capturing edge details, recognizing local textures and modeling spatial continuity, this paper proposes a novel decoder framework specifically designed for medical image segmentation, comprising three core modules. First, the Adaptive Cross-Fusio
Despite the progress made through deep learning, existing Visual Object Tracking (VOT) frameworks struggle with real-world challenges. Recent approaches incorporate additional modalities like Depth, Thermal Infrared, and Language to enhance the robustness of VOT, particularly with the improvement of
Visible-Infrared (RGB-IR) Unmanned Aerial Vehicle (UAV) object detection integrates complementary cues from visible and infrared sensors, offering broad application potential. However, due to sensor parallax, it still faces the challenge of weak spatial misalignment, which significantly limits its p
Deep learning has shown strong performance in time series forecasting tasks. However, issues such as missing values and anomalies in sequential data hinder its further development in prediction tasks. Previous research has primarily focused on extracting feature information from sequence data or add
Mainstream methods for multivariate time-series forecasting largely follow the Direct-Mapping paradigm. They learn a unified mapping from history to the future in the observation space to fit value-level dependencies. However, real-world systems often undergo distribution shifts and regime changes. …
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}…
Automated analysis of temporal changes in multimodal retinal images is critical for the prognostic assessment of ophthalmic diseases. Unlike traditional single-timepoint diagnosis, tracking longitudinal changes across multiple imaging modalities introduces significant data bias challenges: (1) Imbal
Neural textures have emerged as pivotal assets in next-generation neural rendering pipelines. However, hardware limitations and programming interface constraints lead to suboptimal performance in multi-instance real-time rendering scenarios. This bottleneck becomes particularly acute for texture-int
Deep forecasting models often suffer from attenuated periodic perception and entangled trend–noise representations as network depth increases. Moreover, the widely adopted channel-independent paradigm, while improving training stability, disrupts intrinsic dynamic coordination among variables, hinde…
Multimodal large reasoning models (MLRMs) often suffer from hallucinations that stem not only from insufficient visual grounding but also from imbalanced allocation between perception and reasoning processes. Building upon recent interpretability findings suggesting a staged division of attention ac
Large-scale alignment pipelines typically pair a policy model with a separately trained reward model whose parameters remain frozen during reinforcement learning (RL). This separation creates a complex, resource-intensive pipeline and leads to a performance ceiling. We propose a novel framework, Uni
Multivariate time series forecasting is critical in many real-world systems, and thus modeling cross-channel dependencies is essential. Although existing methods improve overall accuracy by enhancing representations and cross-channel interactions, it remains challenging to reliably capture inter-var…
Current Retrieval-Augmented Generation (RAG) systems concatenate and process numerous retrieved document chunks for prefill which requires a large volume of computation, therefore leading to significant latency in time-to-first-token (TTFT). To reduce the computation overhead as well as TTFT, we int
Recent studies have raised questions about the suitability of the Transformer architecture for long sequence time-series forecasting. These forecasting models leverage Transformers to capture dependencies between multiple time steps in a time series, with embedding tokens composed of data from indiv…
The 3D reconstruction of patient specific bone models plays a crucial role in orthopaedic surgery for clinical evaluation, surgical planning and precise implant design or selection. This paper considers the problem of reconstructing a patient-specific 3D tibia and fibula model from only two 2D X-ray…
Hyperparameter optimization, also known as hyperparameter tuning, is a widely recognized technique for improving model performance. Regrettably, when training private ML models, many practitioners often overlook the privacy risks associated with hyperparameter optimization, which could potentially e…
The quality of a blastocyst directly determines the embryo's implantation potential, thus making it essential to objectively and accurately identify the blastocyst morphology. In this work, we propose an automatic framework named I2CNet to perform the blastocyst segmentation task in human embryo ima…
Link prediction is the task of inferring missing links between entities in knowledge graphs. Embedding-based methods have shown effectiveness in addressing this problem by modeling relational patterns in triples. However, the link prediction task often requires contextual information in entity neigh…
Understanding the training dynamics of deep learning models is perhaps a necessary step toward demystifying the effectiveness of these models. In particular, how do training data from different classes gradually become separable in their feature spaces when training neural networks using stochastic…
Alzheimer’s Disease (AD) is a chronic neurodegenerative disease that causes severe problems in patients’ thinking, memory, and behavior. An early diagnosis is crucial to prevent AD progression; to this end, many algorithmic approaches have recently been proposed to predict cognitive decline. However…
Recognition of group activities is critical for the success of applications that depend on effective human-robot teaming. Awareness of these group activities (also referred to team behaviors in some literature), including the individual activities of human teammates and the overall team intent, allo
With rapid progress in high-throughput genotyping and neuroimaging, researches of complex brain disorders, such as Alzheimer's Disease (AD), have gained significant attention in recent years. Many prediction models have been studied to relate neuroimaging measures to cognitive status over the progre…
A fundamental problem in high-dimensional regression is to understand the tradeoff between type I and type II errors or, equivalently, false discovery rate (FDR) and power in variable selection. To address this important problem, we offer the first complete diagram that distinguishes all pairs of FD…
This paper puts forward a LSTM and CNN based assemble neural network framework to distinguish different types of arrhythmias by integrating stacked bidirectional long shot-term memory (SB-LSTM) network and two-dimensional convolutional neural network (TD-CNN). Particularly, SB-LSTM is used to mine t…
Multi-instance learning (MIL) has demonstrated its usefulness in many real-world image applications in recent years. However, two critical challenges prevent one from effectively using MIL in practice. First, existing MIL methods routinely model the predictive targets using the instances of input im…
Place recognition plays an important role to perform loop closure detection of large-scale, long-term simultaneous localization and mapping in loopy environments. The long-term place recognition problem is challenging because the environment appearance exhibits significant long-term variations acros
Loop closure detection is an essential component for simultaneously localization and mapping in a variety of robotics applications. One of the most challenging problems is to perform long-term place recognition with strong perceptual aliasing and appearance variations due to changes of illumination,…