Stay updated with the latest research and technology news
arXiv:2507.09193v2 Announce Type: replace Abstract: The problem of bistatic integrated sensing and communications over memoryless relay channels is considered, where destination concurrently decodes the message...
arXiv:2507.09768v3 Announce Type: replace Abstract: In recent years, deep learning-based single-channel speech separation has improved considerably, in large part driven by increasingly compute- and parameter-efficient...
arXiv:2507.09875v3 Announce Type: replace Abstract: Large language models demonstrate the intriguing ability to perform unseen tasks via in-context learning. However, it remains unclear what mechanisms...
arXiv:2507.13231v4 Announce Type: replace Abstract: Conventional flow matching and diffusion-based policies sample via iterative denoising from standard noise distributions (e.g., Gaussian), and require conditioning modules...
arXiv:2507.15518v4 Announce Type: replace Abstract: Creating an immersive and interactive theatrical experience is a long-term goal in the field of interactive narrative. The emergence of...
arXiv:2507.15557v2 Announce Type: replace Abstract: Despite notable advances in large language models (LLMs), reliable evaluation of text generation tasks such as text style transfer (TST)...
arXiv:2507.15796v2 Announce Type: replace Abstract: Federated Learning (FL) enables privacy-preserving collaborative learning, yet deployments increasingly show that privacy guarantees alone do not sustain trust in...
arXiv:2507.16405v2 Announce Type: replace Abstract: Inductive Logic Programming (ILP) approaches like Meta \-/ Interpretive Learning (MIL) can learn, from few examples, recursive logic programs with...
arXiv:2507.16553v2 Announce Type: replace Abstract: In this study, we propose a robust control strategy for a counter-current heat exchanger. The primary objective is to regulate...
arXiv:2507.16810v3 Announce Type: replace Abstract: We consider an inverse initial-data problem for the compressible anisotropic Navier--Stokes equations, in which the goal is to reconstruct the...
arXiv:2507.19819v3 Announce Type: replace Abstract: Industry adoption of chiplets has been growing as chiplets are a cost-effective option for making large, high-performance systems. Consequently, partitioning...
arXiv:2507.23199v2 Announce Type: replace Abstract: We consider the filtering problem with the partially observed Lorenz 96 model. Although the accuracy of the 3DVar filter in...
arXiv:2508.00450v3 Announce Type: replace Abstract: Traditional recommendation systems tend to trap users in strong feedback loops by excessively pushing content aligned with their historical preferences,...
arXiv:2508.01222v2 Announce Type: replace Abstract: Many real-world data science tasks involve complex web-based interactions: finding appropriate data available on the internet, synthesizing multimodal data from...
arXiv:2508.01603v4 Announce Type: replace Abstract: In AI-generated image detection, current cutting-edge methods typically adapt pre-trained foundation models through partial-parameter fine-tuning. However, these approaches often struggle...
arXiv:2508.03099v2 Announce Type: replace Abstract: We propose Point2Act, which directly retrieves the 3D action point relevant to a contextually described task, leveraging Multimodal Large Language...
arXiv:2508.03284v2 Announce Type: replace Abstract: Integrating external tools into Large Foundation Models (LFMs) has emerged as a promising approach to enhance their problem-solving capabilities. While...
arXiv:2508.04975v2 Announce Type: replace Abstract: Traditionally, traders and quantitative analysts address alpha decay by manually crafting formulaic alphas, mathematical expressions that identify patterns or signals...
arXiv:2508.06066v3 Announce Type: replace Abstract: Learning from time series is fundamentally different from learning from i.i.d.\ data: temporal dependence can make long sequences effectively information-poor,...
arXiv:2508.06803v2 Announce Type: replace Abstract: Sarcasm detection is a crucial yet challenging Natural Language Processing task. Existing Large Language Model methods are often limited by...
arXiv:2508.07321v2 Announce Type: replace Abstract: The rapid proliferation of Large Language Models (LLMs) has significantly contributed to the development of equitable AI systems capable of...
arXiv:2508.07782v2 Announce Type: replace Abstract: Recent advancements in gait recognition have significantly enhanced performance by treating silhouettes as either an unordered set or an ordered...
arXiv:2508.11025v3 Announce Type: replace Abstract: Conformal prediction is a popular uncertainty quantification method that augments a base predictor to return sets of predictions with statistically...
arXiv:2508.11147v2 Announce Type: replace Abstract: Mobile application performance is a vital factor for user experience. Yet, performance issues are notoriously difficult to detect in development...