Stay updated with the latest research and technology news
arXiv:2601.21615v1 Announce Type: new Abstract: Graph Neural Networks frequently exhibit significant performance degradation in the out-of-distribution test scenario. While test-time training (TTT) offers a promising...
arXiv:2601.21617v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are advancing computational pathology with superior visual understanding capabilities. However, current systems often reduce diagnosis to directly...
arXiv:2601.21618v1 Announce Type: new Abstract: Counting should not depend on what is being counted; more generally, any algorithm's behavior should be invariant to the semantic...
arXiv:2601.21619v1 Announce Type: new Abstract: Parallel thinking enhances LLM reasoning by multi-path sampling and aggregation. In system-level evaluations, a global parallelism level N is allocated...
arXiv:2601.21621v1 Announce Type: new Abstract: Recent literature suggests that the bigger the model, the more likely it is to converge to similar, ``universal'' representations, despite...
arXiv:2601.21622v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by separating token proposal from verification, but most existing approaches are designed for single-node execution...
arXiv:2601.21623v1 Announce Type: new Abstract: Mixed-precision computations are a hallmark of the current stage of AI, driving the progress in large language models towards efficient,...
arXiv:2601.21624v1 Announce Type: new Abstract: Modern deep-learning training is not memoryless. Updates depend on optimizer moments and averaging, data-order policies (random reshuffling vs with-replacement, staged...
arXiv:2601.21626v1 Announce Type: new Abstract: Post Training Quantization (PTQ), a mainstream model compression technique, often leads to the paradoxical 'low error, high loss' phenomenon because...
arXiv:2601.21628v1 Announce Type: new Abstract: Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy. In particular,...
arXiv:2601.21631v1 Announce Type: new Abstract: Most classroom engagements with generative AI focus on prompting pre-trained models, leaving the role of training data and model mechanics...
arXiv:2601.21632v1 Announce Type: new Abstract: Open-source AI is scaling rapidly, and model hubs now host millions of artifacts. Each foundation model can spawn large numbers...
arXiv:2601.21633v1 Announce Type: new Abstract: In latent diffusion models, the autoencoder (AE) is typically expected to balance two capabilities: faithful reconstruction and a generation-friendly latent...
arXiv:2601.21634v1 Announce Type: new Abstract: Remote Sensing Visual Grounding (RSVG) aims to localize target objects in large-scale aerial imagery based on natural language descriptions. Owing...
arXiv:2601.21635v1 Announce Type: new Abstract: In this work, we study a primal hybrid finite element method for the approximation of linear elasticity problems, posed in...
arXiv:2601.21636v1 Announce Type: new Abstract: We study privacy amplification for differentially private model training with matrix factorization under random allocation (also known as the balls-in-bins...
arXiv:2601.21637v1 Announce Type: new Abstract: In this paper, we explore the use of generative artificial intelligence (GenAI) for ship propeller design. While traditional forward machine...
arXiv:2601.21639v1 Announce Type: new Abstract: The development of large vision language models drives the demand for managing, and applying massive amounts of multimodal data, making...
arXiv:2601.21641v1 Announce Type: new Abstract: Transformer-based models have recently made significant advances in accurate time-series forecasting, but even these architectures struggle to scale efficiently while...
arXiv:2601.21645v1 Announce Type: new Abstract: We investigate the relation between end-to-end equivariance and layerwise equivariance in deep neural networks. We prove the following: For a...
arXiv:2601.21647v1 Announce Type: new Abstract: Discrete Diffusion Language Models (DLMs) offer a promising non-autoregressive alternative for text generation, yet effective mechanisms for inference-time control remain...
arXiv:2601.21648v1 Announce Type: new Abstract: Depression is a prevalent mental health disorder that severely impairs daily functioning and quality of life. While recent deep learning...
arXiv:2601.21649v1 Announce Type: new Abstract: The deployment of coding agents in privacy-sensitive and resource-constrained environments drives the demand for capable open-weight Small Language Models (SLMs)....
arXiv:2601.21650v1 Announce Type: new Abstract: AI consumer markets are characterized by severe buyer-supplier market asymmetries. Complex AI systems can appear highly accurate while making costly...