Stay updated with the latest research and technology news
arXiv:2601.20299v1 Announce Type: new Abstract: The evaluation and post-training of large language models (LLMs) rely on supervision, but strong supervision for difficult tasks is often...
arXiv:2601.20300v1 Announce Type: new Abstract: Self-supervised learning (SSL) has greatly advanced speech representation learning, but multilingual SSL models remain constrained to languages encountered during pretraining....
arXiv:2601.20301v1 Announce Type: new Abstract: Sharpness-Aware Minimization (SAM) has recently emerged as an effective technique for improving DNN robustness to input variations. However, its interplay...
arXiv:2601.20302v1 Announce Type: new Abstract: Performance degradation due to covariate shift remains a major challenge for deep learning models in medical image segmentation. An open...
arXiv:2601.20303v1 Announce Type: new Abstract: Estimating object mass from visual input is challenging because mass depends jointly on geometric volume and material-dependent density, neither of...
arXiv:2601.20304v1 Announce Type: new Abstract: The application of iodinated contrast media (ICM) improves the sensitivity and specificity of computed tomography (CT) for a wide range...
arXiv:2601.20305v1 Announce Type: new Abstract: Unified Multimodal Models (UMMs) exhibit strong understanding, yet this capability often fails to effectively guide generation. We identify this as...
arXiv:2601.20306v1 Announce Type: new Abstract: All-in-one image restoration aims to address diverse degradation types using a single unified model. Existing methods typically rely on degradation...
arXiv:2601.20307v1 Announce Type: new Abstract: The prediction objectives of online advertisement ranking models are evolving from probabilistic metrics like conversion rate (CVR) to numerical business...
arXiv:2601.20308v1 Announce Type: new Abstract: Diffusion models (DMs) have demonstrated exceptional success in video super-resolution (VSR), showcasing a powerful capacity for generating fine-grained details. However,...
arXiv:2601.20309v1 Announce Type: new Abstract: Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memory...
arXiv:2601.20310v1 Announce Type: new Abstract: Latent-based watermarks, integrated into the generation process of latent diffusion models (LDMs), simplify detection and attribution of generated images. However,...
arXiv:2601.20311v1 Announce Type: new Abstract: The global shortage and uneven distribution of medical expertise continue to hinder equitable access to accurate diagnostic care. While existing...
arXiv:2601.20312v1 Announce Type: new Abstract: Existing self-evolution methods overlook the influence of fine-grained reasoning steps, which leads to the reasoner-verifier gap. The computational inefficiency of...
arXiv:2601.20314v1 Announce Type: new Abstract: We study dual-unmanned aerial vehicle (UAV) jamming-aided secure communication networks, in which one UAV delivers confidential data to multiple ground...
arXiv:2601.20316v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed for personalized product recommendations, with practitioners commonly assuming that longer user purchase histories...
arXiv:2601.20317v1 Announce Type: new Abstract: The Visual Geometry Grounded Transformer (VGGT) enables strong feed-forward 3D reconstruction without per-scene optimization. However, its billion-parameter scale creates high...
arXiv:2601.20318v1 Announce Type: new Abstract: Current methods for multivariate time series forecasting can be classified into channel-dependent and channel-independent models. Channel-dependent models learn cross-channel features...
arXiv:2601.20321v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently emerged as powerful generalists for robotic manipulation. However, due to their predominant reliance on visual...
arXiv:2601.20323v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models have rapidly expanded to electrocardiograms, focusing on classification, report generation, and single-turn QA...
arXiv:2601.20324v1 Announce Type: new Abstract: Providing formal guarantees for neural network-based controllers in large-scale interconnected systems remains a fundamental challenge. In particular, using neural certificates...
arXiv:2601.20325v1 Announce Type: new Abstract: Machine unlearning is an emerging technique that aims to remove the influence of specific data from trained models, thereby enhancing...
arXiv:2601.20326v1 Announce Type: new Abstract: KV caches, typically used only to speed up autoregressive decoding, encode contextual information that can be reused for downstream tasks...
arXiv:2601.20327v1 Announce Type: new Abstract: Automatic evaluation is crucial yet challenging for open-ended natural language generation, especially when rule-based metrics are infeasible. Compared with traditional...