Stay updated with the latest research and technology news
arXiv:2601.15122v2 Announce Type: replace Abstract: Popularity bias is a pervasive challenge in recommender systems, where a few popular items dominate attention while the majority of...
arXiv:2601.15127v2 Announce Type: replace Abstract: Federated Neural Architecture Search (FedNAS) aims to automate model design for privacy-preserving Federated Learning (FL) but currently faces two critical...
arXiv:2601.15550v2 Announce Type: replace Abstract: Existing cultural commonsense benchmarks treat nations as monolithic, assuming uniform practices within national boundaries. But does cultural commonsense hold uniformly...
arXiv:2601.16200v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) exhibit strong capabilities across diverse applications, yet remain vulnerable to adversarial perturbations that distort their...
arXiv:2601.16752v2 Announce Type: replace Abstract: Obtaining meaningful and informed consent from users is essential for ensuring autonomy and control over one's data. Notice and consent,...
arXiv:2601.16836v2 Announce Type: replace Abstract: While text-to-image (T2I) models have advanced considerably, their capability to associate colors with implicit concepts remains underexplored. To address the...
arXiv:2601.16991v2 Announce Type: replace Abstract: Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates,...
arXiv:2601.17046v3 Announce Type: replace Abstract: We present a novel approach for extracting 3D atomic-level information from transmission electron microscopy (TEM) images affected by significant noise....
arXiv:2601.17087v2 Announce Type: replace Abstract: Agentic benchmarks increasingly rely on LLM-simulated users to scalably evaluate agent performance, yet the robustness, validity, and fairness of this...
arXiv:2601.17136v2 Announce Type: replace Abstract: Clustering is an important tool in data analysis, with K-means being popular for its simplicity and versatility. However, it cannot...
arXiv:2601.17196v2 Announce Type: replace Abstract: Partial Optimal Transport (POT) addresses the problem of transporting only a fraction of the total mass between two distributions, making...
arXiv:2601.17216v2 Announce Type: replace Abstract: Intelligent Transportation Systems (ITS) demand real-time collision prediction to ensure road safety and reduce accident severity. Conventional approaches rely on...
arXiv:2601.17261v2 Announce Type: replace Abstract: Zeroth-Order (ZO) optimization has emerged as a promising solution for fine-tuning LLMs under strict memory constraints, as it avoids the...
arXiv:2601.17354v2 Announce Type: replace Abstract: Efficient and high-fidelity 3D scene modeling is a long-standing pursuit in computer graphics. While recent 3D Gaussian Splatting (3DGS) methods...
arXiv:2601.17367v2 Announce Type: replace Abstract: The quadratic complexity of standard attention mechanisms poses a significant scalability bottleneck for large language models (LLMs) in long-context scenarios....
arXiv:2601.17517v2 Announce Type: replace Abstract: Audio codecs power discrete music generative modelling, music streaming and immersive media by shrinking PCM audio to bandwidth-friendly bit-rates. Recent...
arXiv:2601.17607v2 Announce Type: replace Abstract: Learning systems acquire structured internal representations from data, yet classical information-theoretic results state that deterministic transformations do not increase information....
arXiv:2601.17702v2 Announce Type: replace Abstract: Large language models are increasingly applied to multi-document and long-form inputs, yet long-context inference remains memory- and noise-inefficient. Key-value (KV)...
arXiv:2601.17934v2 Announce Type: replace Abstract: Foundation models like the Segment Anything Model (SAM) show strong generalization, yet adapting them to medical images remains difficult due...
arXiv:2601.17957v2 Announce Type: replace Abstract: Grassroots Logic Programs (GLP) is a concurrent logic programming language in which logic variables are partitioned into paired readers and...
arXiv:2601.18442v2 Announce Type: replace Abstract: Autonomous vehicle safety validation requires testing on safety-critical scenarios, but these events are rare in real-world driving and costly to...
arXiv:2601.18543v2 Announce Type: replace Abstract: We introduce GenAgent, unifying visual understanding and generation through an agentic multimodal model. Unlike unified models that face expensive training...
arXiv:2601.18631v2 Announce Type: replace Abstract: When humans face problems beyond their immediate capabilities, they rely on tools, providing a promising paradigm for improving visual reasoning...
arXiv:2601.18697v2 Announce Type: replace Abstract: LLM-based chatbots like ChatGPT have become popular tools for assisting with coding tasks. However, they often produce isolated responses and...