Multimodal foundation models integrate heterogeneous signals across modalities, yet it remains poorly understood how their predictions depend on specific intern...
Ultrafast online learning is essential for high-frequency systems, such as controls for quantum computing and nuclear fusion, where adaptation must occur on sub...
In Internet-of-Things systems, federated learning has advanced online reinforcement learning (RL) by enabling parallel policy training without sharing raw data....
Graph-based Retrieval-Augmented Generation (GraphRAG) organizes external knowledge as a hierarchical graph, enabling efficient retrieval and aggregation of scat...
Text-to-image diffusion models have revolutionized generative AI, enabling high-quality and photorealistic image synthesis. However, their practical deployment ...
Diffusion models have recently emerged as powerful learned priors for Bayesian inverse problems (BIPs). Diffusion-based solvers rely on a presumed likelihood fo...
The increasing availability of relational data has contributed to a growing reliance on network-based representations of complex systems. Over time, these model...
The agency expected of Agentic Large Language Models goes beyond answering correctly, requiring autonomy to set goals and decide what to explore. We term this i...
Advertising image generation has increasingly focused on online metrics like Click-Through Rate (CTR), yet existing approaches adopt a ``one-size-fits-all' stra...
We establish a theoretical connection between wavelet transforms and spiking neural networks through scale-space theory. We rely on the scale-covariant guarante...
Recent genomic foundation models largely adopt large language model architectures that treat DNA as a one-dimensional token sequence. However, exhaustive sequen...
Large Reasoning Models (LRMs) often suffer from overthinking, a phenomenon in which redundant reasoning steps are generated after a correct solution has already...
World models have demonstrated significant promise for data synthesis in autonomous driving. However, existing methods predominantly concentrate on single-modal...
Reconstructing 3D scenes from sparse images remains a challenging task due to the difficulty of recovering accurate geometry and texture without optimization. R...
Neuromorphic hardware implementations of Spiking Neural Networks (SNNs) promise energy-efficient, low-latency AI through sparse, event-driven computation. Yet, ...
Cross-partition edges dominate the cost of distributed GNN training: fetching remote features and activations per iteration overwhelms the network as graphs dee...
Federated Unlearning (FU) aims to efficiently remove the influence of specific client data from a federated model while preserving utility for the remaining cli...
Genetic programming-based feature construction has achieved significant success in recent years as an automated machine learning technique to enhance learning p...
We propose a neuromorphic solver for the NP-hard Edge User Allocation problem using an attractor network with Winner-Takes-All (WTA) mechanism implemented with ...
Since Differential Evolution (DE) is sensitive to strategy choice, most existing variants pursue performance through adaptive mechanisms or intricate designs. W...
While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulti...
Shared autonomy systems require principled methods for inferring user intent and determining appropriate assistance levels. This is a central challenge in human...
Open-set object detection (OSOD) localizes objects while identifying and rejecting unknown classes at inference. While recent OSOD models perform well on benchm...
We propose a data-efficient, physics-aware generative framework in function space for inverse PDE problems. Existing plug-and-play diffusion posterior samplers ...
