Stay updated with the latest research and technology news
arXiv:2603.00541v1 Announce Type: new Abstract: Generative foundation models are increasingly scaled in both width and depth, posing significant challenges for stable feature learning and reliable...
arXiv:2603.00542v1 Announce Type: new Abstract: In real-world vision systems,haze removal is required not only to enhance image visibility but also to meet the specific needs...
arXiv:2603.00543v1 Announce Type: new Abstract: Pansharpening aims to generate high-resolution multi-spectral images by fusing the spatial detail of panchromatic images with the spectral richness of...
arXiv:2603.00544v1 Announce Type: new Abstract: One-time programs (OTPs) aim to let a user evaluate a program on a single input while revealing nothing else. Classical...
arXiv:2603.00545v1 Announce Type: new Abstract: The current methods for diagnosing Alzheimer Disease using Magnetic Resonance Imaging (MRI) have significant limitations. Many previous studies used 2D...
arXiv:2603.00546v1 Announce Type: new Abstract: Using Multimodal Large Language Models (MLLMs) as judges to achieve precise and consistent evaluations has gradually become an emerging paradigm...
arXiv:2603.00549v1 Announce Type: new Abstract: We present PM2Lat, a fast and generalized framework for accurately predicting the latency of deep neural network models on GPUs,...
arXiv:2603.00550v1 Announce Type: new Abstract: Weakly supervised video anomaly detection (WS-VAD) involves identifying the temporal intervals that contain anomalous events in untrimmed videos, where only...
arXiv:2603.00551v1 Announce Type: new Abstract: GPU architectural simulation is orders of magnitude slower than native execution, necessitating workload sampling for practical speedups. Existing methods rely...
arXiv:2603.00552v1 Announce Type: new Abstract: Evaluating persona-aligned empathy in LLM-based dialogue agents remains challenging. User states are latent, feedback is sparse and difficult to verify...
arXiv:2603.00560v1 Announce Type: new Abstract: In operating rooms (OR), world-scale multi-view 3D tracking supports downstream applications such as surgeon behavior recognition, where physically meaningful quantities...
arXiv:2603.00563v1 Announce Type: new Abstract: The Transformer-based Whisper model has achieved state-of-the-art performance in Automatic Speech Recognition (ASR). However, its Multi-Head Attention (MHA) mechanism results...
arXiv:2603.00565v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful content...
arXiv:2603.00567v1 Announce Type: new Abstract: Neural contextual bandits are vulnerable to adversarial attacks, where subtle perturbations to rewards, actions, or contexts induce suboptimal decisions. We...
arXiv:2603.00568v1 Announce Type: new Abstract: Molecule representation learning is crucial for understanding and predicting molecular properties. However, conventional atom-centric models, which treat chemical bonds merely...
arXiv:2603.00569v1 Announce Type: new Abstract: TopoEdge is a topology-grounded, edge-deployable framework for end-to-end software-defined networking (SDN) configuration generation and repair, motivated by the brittleness of...
arXiv:2603.00573v1 Announce Type: new Abstract: Large language models (LLMs) achieve remarkable performance on diverse downstream and domain-specific tasks via parameter-efficient fine-tuning (PEFT). However, existing PEFT...
arXiv:2603.00574v1 Announce Type: new Abstract: Adapting pretrained multi-modal models to evolving test-time distributions, known as multi-modal test-time adaptation, presents a significant challenge. Existing methods frequently...
arXiv:2603.00575v1 Announce Type: new Abstract: Progress in software-engineering agents is increasingly constrained by the scarcity of executable, scalable, and realistic data for training and evaluation....
arXiv:2603.00576v1 Announce Type: new Abstract: Symbolic music generation is a challenging task in multimedia generation, involving long sequences with hierarchical temporal structures, long-range dependencies, and...
arXiv:2603.00578v1 Announce Type: new Abstract: Long chain-of-thought~(CoT) has become a dominant paradigm for enhancing the reasoning capability of large reasoning models~(LRMs); however, the performance gains...
arXiv:2603.00579v1 Announce Type: new Abstract: Federated Learning (FL) is a popular distributed learning paradigm to break down data silo. Traditional FL approaches largely rely on...
arXiv:2603.00582v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated proficiency in Deep Research or Wide Search, their capacity to solve highly complex...
arXiv:2603.00585v1 Announce Type: new Abstract: Recent advances in video generation have opened new avenues for macroscopic simulation of complex dynamic systems, but their application to...