Stay updated with the latest research and technology news
arXiv:2601.15727v2 Announce Type: replace Abstract: The performance of modern AI systems is fundamentally constrained by the quality of their underlying kernels, which translate high-level algorithmic...
arXiv:2601.15946v2 Announce Type: replace Abstract: Accurate calibration and robust localization are fundamental for downstream tasks in spinning actuated LiDAR applications. Existing methods, however, require parameterizing...
arXiv:2601.15992v2 Announce Type: replace Abstract: With the increasing use of RDF graphs, storing and querying such data using SPARQL remains a critical problem. Current mainstream...
arXiv:2601.16032v2 Announce Type: replace Abstract: High-performance attention kernels are essential for Large Language Models. This paper presents analysis of CuTile-based Flash Attention memory behavior and...
arXiv:2601.16034v2 Announce Type: replace Abstract: Refusal behavior in aligned LLMs is often viewed as model-specific, yet we hypothesize it stems from a universal, low-dimensional semantic...
arXiv:2601.16072v2 Announce Type: replace Abstract: We study Constrained Online Convex Optimization (COCO), where a learner chooses actions iteratively, observes both unanticipated convex loss and convex...
arXiv:2601.16078v2 Announce Type: replace Abstract: One of the core advantages of SE2(3) Lie group framework for navigation modeling lies in the autonomy of error propagation....
arXiv:2601.16199v2 Announce Type: replace Abstract: Machine learning property attestations allow provers (e.g., model providers or owners) to attest properties of their models/datasets to verifiers (e.g.,...
arXiv:2601.16212v2 Announce Type: replace Abstract: Robot foundation models are beginning to deliver on the promise of generalist robotic agents, yet progress remains constrained by the...
arXiv:2601.16249v2 Announce Type: replace Abstract: Learning DAG structures from purely observational data remains a long-standing challenge across scientific domains. An emerging line of research leverages...
arXiv:2601.16399v2 Announce Type: replace Abstract: We study a structured bi-level optimization problem where the upper-level objective is a smooth function and the lower-level problem is...
arXiv:2601.16432v2 Announce Type: replace Abstract: Structured Query Language (SQL) has remained the standard query language for databases. SQL is highly optimized for processing structured data...
arXiv:2601.16444v2 Announce Type: replace Abstract: "LLM-as-a-judge," which utilizes large language models (LLMs) as evaluators, has proven effective in many evaluation tasks. However, evaluator LLMs exhibit...
arXiv:2601.16502v2 Announce Type: replace Abstract: Artificial-intelligence (AI) workloads are driving rapid growth in data-center electricity use and rack power density, increasing demand for power-delivery systems...
arXiv:2601.16516v2 Announce Type: replace Abstract: Time series data from the Intensive Care Unit (ICU) provides critical information for patient monitoring. While recent advancements in applying...
arXiv:2601.16531v2 Announce Type: replace Abstract: We investigate whether high-frequency key collisions are a primary bottleneck in Engram-style conditional memory. To isolate the effect of collisions,...
arXiv:2601.16532v2 Announce Type: replace Abstract: Single-view indoor scene generation plays a crucial role in a range of real-world applications. However, generating a complete 360{\deg} scene...
arXiv:2601.16736v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for real-time novel view synthesis. As an explicit representation optimized...
arXiv:2601.16781v2 Announce Type: replace Abstract: In-context knowledge editing (IKE) is a promising technique for updating Large Language Models (LLMs) with new information. However, IKE relies...
arXiv:2601.16799v2 Announce Type: replace Abstract: The 6G communication systems use mmWave and MIMO technologies to achieve wide bandwidth and high throughout, leading to indispensable need...
arXiv:2601.16872v2 Announce Type: replace Abstract: User behavior modeling lies at the heart of personalized applications like recommender systems. With LLM-based agents, user preference representation has...
arXiv:2601.16882v2 Announce Type: replace Abstract: Group recommender systems help users make collective choices but often lack transparency, leaving group members uncertain about why items are...
arXiv:2601.16885v2 Announce Type: replace Abstract: Transformer-based general visual geometry frameworks have shown promising performance in camera pose estimation and 3D scene understanding. Recent advancements in...
arXiv:2110.07478v4 Announce Type: replace-cross Abstract: It is often of interest to infer lower-dimensional structure underlying complex data. As a flexible class of non-linear structures, it...