Stay updated with the latest research and technology news
arXiv:2603.02678v2 Announce Type: replace Abstract: Learning causal structures typically represented by directed acyclic graphs (DAGs) from observational data is notoriously challenging due to the combinatorial...
arXiv:2603.02686v2 Announce Type: replace Abstract: Despite the success of large language models (LLMs) across domains, their potential for efficient channel state information (CSI) compression and...
arXiv:2603.02743v2 Announce Type: replace Abstract: Realistic shadow generation is crucial for achieving seamless image compositing, yet existing methods primarily focus on single-object insertion and often...
arXiv:2603.02767v2 Announce Type: replace Abstract: Image-text contrastive pretraining has become a dominant paradigm for visual representation learning, yet existing methods often yield representations that remain...
arXiv:2603.02829v2 Announce Type: replace Abstract: Recent text-to-image (T2I) diffusion and flow-matching models can produce highly realistic images from natural language prompts. In practical scenarios, T2I...
arXiv:2603.02862v2 Announce Type: replace Abstract: Reinforcement learning algorithms are typically designed for generic Markov Decision Processes (MDPs), where any state-action pair can lead to an...
arXiv:2603.02873v2 Announce Type: replace Abstract: As large language models (LLMs) increasingly assist scientific writing, limitations and the significant token cost of TeX become more and...
arXiv:2603.02887v2 Announce Type: replace Abstract: In this work we generalize 3D Gaussian splatting (3DGS) to a wider family of physically-based alpha-blending operators. 3DGS has become...
arXiv:2603.02909v2 Announce Type: replace Abstract: Document-level event argument extraction (DEAE) is essential for knowledge acquisition, aiming to extract participants of events from documents . In...
arXiv:2603.02929v2 Announce Type: replace Abstract: Universal Multimodal Retrieval requires unified embedding models capable of interpreting diverse user intents, ranging from simple keywords to complex compositional...
arXiv:2603.02989v2 Announce Type: replace Abstract: Footstep planning involves a challenging combinatorial search. Traditional A* approaches require discretising reachability constraints, while Mixed-Integer Programming (MIP) supports continuous...
arXiv:2603.02999v2 Announce Type: replace Abstract: The end-to-end generative paradigm is revolutionizing advertising recommendation systems, driving a shift from traditional cascaded architectures towards unified modeling. However,...
arXiv:2603.03101v2 Announce Type: replace Abstract: The CLIP model's outstanding generalization has driven recent success in Zero-Shot Anomaly Detection (ZSAD) for detecting anomalies in unseen categories....
arXiv:2603.03140v2 Announce Type: replace Abstract: AI agents are increasingly active on social media platforms, generating content and interacting with one another at scale. Yet the...
arXiv:2603.03187v2 Announce Type: replace Abstract: Medical image segmentation commonly relies on U-shaped encoder-decoder architectures such as U-Net, where skip connections preserve fine spatial detail by...
arXiv:2603.03197v2 Announce Type: replace Abstract: Classifying fine-grained visual concepts under open-world settings, i.e., without a predefined label set, demands models to be both accurate and...
arXiv:2603.03202v2 Announce Type: replace Abstract: As large language models (LLMs) advance their mathematical capabilities toward the IMO level, the scarcity of challenging, high-quality problems for...
arXiv:cs/0507027v5 Announce Type: replace Abstract: Preference aggregation in a multiagent setting is a central issue in both human and computer contexts. In this paper, we...
arXiv:2312.05645v2 Announce Type: replace-cross Abstract: We study the problem of hypothesis selection under the constraint of local differential privacy. Given a class $\mathcal{F}$ of $k$...
arXiv:2404.03813v5 Announce Type: replace-cross Abstract: We define a quantum learning task called agnostic tomography, where given copies of an arbitrary state $\rho$ and a class...
arXiv:2407.13728v4 Announce Type: replace-cross Abstract: Quantum state exclusion is an operational task with application to ontological interpretations of quantum states. In such a task, one...
arXiv:2412.19436v2 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) has become a cornerstone for aligning large language models with human preferences. However, the...
arXiv:2501.07461v3 Announce Type: replace-cross Abstract: In this paper we propose a framework to analyze iterative first-order optimization algorithms for time-varying convex optimization. We assume that...
arXiv:2501.18575v4 Announce Type: replace-cross Abstract: The Reynolds equation from lubrication theory and the Stokes equations for zero Reynolds number flows are distinct models for an...