Stay updated with the latest research and technology news
arXiv:2602.19088v2 Announce Type: replace Abstract: Today's distributed systems operate in complex environments that inevitably involve faults and even adversarial behaviors. Predicting their performance under such...
arXiv:2602.19112v2 Announce Type: replace Abstract: Establishing dense correspondences between shapes is a crucial task in computer vision and graphics, while prior approaches depend on near-isometric...
arXiv:2602.19117v2 Announce Type: replace Abstract: Perspective-aware spatial reasoning involves understanding spatial relationships from specific viewpoints-either egocentric (observer-centered) or allocentric (object-centered). While vision-language models (VLMs) perform...
arXiv:2602.19275v2 Announce Type: replace Abstract: Large language models (LLMs) acquire a large amount of knowledge through pre-training on vast and diverse corpora. While this endows...
arXiv:2602.19297v2 Announce Type: replace Abstract: Microfluidic devices have emerged as powerful tools in various laboratory applications, but the complexity of their design limits accessibility for...
arXiv:2602.19477v2 Announce Type: replace Abstract: The sandpile automata of Bak, Tang, and Wiesenfeld (Phys. Rev. Lett., 1987) are a simple model for the diffusion of...
arXiv:2602.19612v2 Announce Type: replace Abstract: Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all...
arXiv:2602.19626v2 Announce Type: replace Abstract: We present Nacrith, a lossless compression system that combines a 135M-parameter transformer language model (SmolLM2-135M) with an ensemble of lightweight...
arXiv:2602.19654v2 Announce Type: replace Abstract: Urban air pollution in megacities poses critical public health challenges, particularly in Delhi National Capital Region (NCR) where severe degradation...
arXiv:2602.19720v2 Announce Type: replace Abstract: Multi-die FPGAs enable device scaling beyond reticle limits but introduce severe interconnect overhead across die boundaries. Inter-die connections, commonly referred...
arXiv:2602.19768v2 Announce Type: replace Abstract: Recent Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities in image understanding and natural language generation. However, current approaches focus predominantly...
arXiv:2602.19863v2 Announce Type: replace Abstract: Foundation models are transforming Earth Observation (EO), yet the diversity of EO sensors and modalities makes a single universal model...
arXiv:2602.19946v2 Announce Type: replace Abstract: Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following. But do they perform well as...
arXiv:2602.20092v2 Announce Type: replace Abstract: The goal of the BabyLM is to stimulate new research connections between cognitive modeling and language model pretraining. We invite...
arXiv:2602.20156v2 Announce Type: replace Abstract: LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users...
arXiv:2602.20161v2 Announce Type: replace Abstract: Unified multimodal models can both understand and generate visual content within a single architecture. Existing models, however, remain data-hungry and...
arXiv:2203.03745v5 Announce Type: replace-cross Abstract: States of open quantum systems often decay continuously under environmental interactions. Quantum Markov semigroups model such processes in dissipative environments....
arXiv:2207.01830v3 Announce Type: replace-cross Abstract: We study the diffusion of a true and a false message (misinformation) when agents are biased and able to verify...
arXiv:2406.06513v3 Announce Type: replace-cross Abstract: The critical exponent of an infinite word $\bf x$ is the supremum, over all finite nonempty factors $f$, of the...
arXiv:2407.12506v3 Announce Type: replace-cross Abstract: Single-pixel cameras are an effective solution for imaging outside the visible spectrum, where traditional CMOS/CCD cameras have challenges. When combined...
arXiv:2410.16106v5 Announce Type: replace-cross Abstract: We investigate the statistical properties of Temporal Difference (TD) learning with Polyak-Ruppert averaging, arguably one of the most widely used...
arXiv:2412.01283v2 Announce Type: replace-cross Abstract: We investigate the structure of Kazhdan-Lusztig polynomials of the symmetric group by leveraging computational approaches from big data, including exploratory...
arXiv:2501.06873v2 Announce Type: replace-cross Abstract: As economics scales, a key bottleneck is representing what papers claim in a comparable, aggregable form. We introduce evidence-annotated claim...
arXiv:2502.15917v2 Announce Type: replace-cross Abstract: Stochastic Unit Commitment (SUC) has been proposed to manage the uncertainties driven by renewable integration, but it leads to significant...