Stay updated with the latest research and technology news
arXiv:2601.00269v2 Announce Type: replace Abstract: Faithfulness hallucinations in VQA occur when vision-language models produce fluent yet visually ungrounded answers, severely undermining their reliability in safety-critical...
arXiv:2601.00533v2 Announce Type: replace Abstract: All-in-one image restoration aims to recover clean images from diverse unknown degradations using a single model. But extending this task...
arXiv:2601.01294v2 Announce Type: replace Abstract: We study timbre transfer as an inference-time editing problem for music audio. Starting from a strong pre-trained latent diffusion model,...
arXiv:2601.02553v2 Announce Type: replace Abstract: To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain...
arXiv:2601.03664v2 Announce Type: replace Abstract: Anomaly detection aims to identify data instances that deviate significantly from majority of data, which has been widely used in...
arXiv:2601.04441v2 Announce Type: replace Abstract: Reinforcement learning in discrete combinatorial action spaces requires searching over exponentially many joint actions to simultaneously select multiple sub-actions that...
arXiv:2601.05194v2 Announce Type: replace Abstract: In this study, we aim to better align fall risk prediction from the Johns Hopkins Fall Risk Assessment Tool (JHFRAT)...
arXiv:2601.06320v2 Announce Type: replace Abstract: Inferring high-dimensional physical states from sparse, ad-hoc sensor arrays is a fundamental challenge across AI for Science, yet standard architectures...
arXiv:2601.07315v3 Announce Type: replace Abstract: Analog mixed-signal circuit sizing involves complex trade-offs within high-dimensional design spaces. Existing automatic analog circuit sizing approaches rely solely on...
arXiv:2601.07599v2 Announce Type: replace Abstract: We derive the likelihood of a raw signal in a single photon avalanche diode (SPAD), given a fixed photon flux....
arXiv:2601.08131v3 Announce Type: replace Abstract: Cross-layer reuse of early attention projections can improve optimization and data efficiency, but it creates a structural conflict: the first...
arXiv:2601.08297v2 Announce Type: replace Abstract: Large Language Models (LLMs) often exhibit slash attention patterns, where attention scores concentrate along the $\Delta$-th sub-diagonal for some offset...
arXiv:2601.08430v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation remains...
arXiv:2601.09110v2 Announce Type: replace Abstract: Few-shot semantic segmentation of time-series remote sensing images remains a critical challenge, particularly in regions where labeled data is scarce...
arXiv:2601.09479v2 Announce Type: replace Abstract: Epidemiological modeling is vital in understanding disease dynamics and guiding public health interventions. This study presents a time-fractional SEIR model...
arXiv:2601.09831v2 Announce Type: replace Abstract: In this work, we provide a new convergence theory for plug-and-play proximal gradient descent (PnP-PGD) under prior mismatch where the...
arXiv:2601.10187v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable strides in multilingual translation but are hindered by a systemic cross-lingual verbosity bias,...
arXiv:2601.10402v3 Announce Type: replace Abstract: The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to...
arXiv:2601.10992v2 Announce Type: replace Abstract: Constant rescaling of a Riemannian metric appears in many computational settings, often through a global scale parameter that is introduced...
arXiv:2601.11589v2 Announce Type: replace Abstract: LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have...
arXiv:2601.11957v2 Announce Type: replace Abstract: Overlapping calendar invitations force busy professionals to repeatedly decide which meetings to attend, reschedule, or decline. We refer to this...
arXiv:2601.12066v2 Announce Type: replace Abstract: Existing video object removal methods predominantly rely on diffusion models following a noise-to-data paradigm, where generation starts from uninformative Gaussian...
arXiv:2601.12361v2 Announce Type: replace Abstract: We study the model checking problem of Hyper2LTL over finite structures. Hyper2LTL is a second-order hyperlogic, that extends the well-studied...
arXiv:2601.12706v2 Announce Type: replace Abstract: Time series data play a critical role in various fields, including finance, healthcare, marketing, and engineering. A wide range of...