Stay updated with the latest research and technology news
arXiv:2512.08445v2 Announce Type: replace Abstract: Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image...
arXiv:2512.08535v3 Announce Type: replace Abstract: Although recent 3D-native generators have made great progress in synthesizing reliable geometry, they still fall short in achieving realistic appearances....
arXiv:2512.08564v2 Announce Type: replace Abstract: This paper presents a modular neural image signal processing (ISP) framework that processes raw inputs and renders high-quality display-referred images....
arXiv:2512.10452v2 Announce Type: replace Abstract: Effective code retrieval is indispensable and it has become an important paradigm to search code in hybrid mode using both...
arXiv:2512.11946v2 Announce Type: replace Abstract: Explainable machine learning techniques have gained increasing attention in engineering applications, especially in aerospace design and analysis, where understanding how...
arXiv:2512.12108v3 Announce Type: replace Abstract: The development of machine learning (ML) models based on computed tomography (CT) imaging has been a major focus due to...
arXiv:2512.13687v2 Announce Type: replace Abstract: The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard...
arXiv:2512.14202v2 Announce Type: replace Abstract: The exponential volume growth of hyperbolic geometry can embed the hierarchical relationships between states in reinforcement learning (RL) with far...
arXiv:2512.15028v5 Announce Type: replace Abstract: The pursuit of high-performance data transfer often focuses on raw network bandwidth, where international links of 100 Gbps or higher...
arXiv:2512.16310v2 Announce Type: replace Abstract: Driven by Large Language Models, the single-agent, multi-tool architecture has become a popular paradigm for autonomous agents. However, this architecture...
arXiv:2512.19535v2 Announce Type: replace Abstract: Vision-language models (VLMs) are commonly trained by directly inserting image tokens from a pretrained vision encoder into the text stream...
arXiv:2512.19554v3 Announce Type: replace Abstract: Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all...
arXiv:2512.22266v2 Announce Type: replace Abstract: The widespread application of Large Language Models (LLMs) has motivated a growing interest in their capacity for processing dynamic graphs....
arXiv:2512.23851v4 Announce Type: replace Abstract: Autoregressive video generation relies on history context for content consistency and storytelling. As video histories grow longer, efficiently encoding them...
arXiv:2601.01144v2 Announce Type: replace Abstract: Visual challenges in underwater environments significantly hinder the accuracy of vision-based localisation and the high-fidelity dense reconstruction. In this paper,...
arXiv:2601.02751v2 Announce Type: replace Abstract: Most membership inference attacks (MIAs) against Large Language Models (LLMs) rely on global signals, like average loss, to identify training...
arXiv:2601.05805v2 Announce Type: replace Abstract: This paper presents InsSo3D, an accurate and efficient method for large-scale 3D Simultaneous Localisation and Mapping (SLAM) using a 3D...
arXiv:2601.06225v2 Announce Type: replace Abstract: Large Language Models (LLMs) offer a promising solution to complement traditional teaching and address global teacher shortages that affect hundreds...
arXiv:2601.06558v2 Announce Type: replace Abstract: Recovering a sparse signal from outlier-contaminated measurements is a fundamental challenge in many applications. While existing algorithms predominantly address scenarios...
arXiv:2601.09648v2 Announce Type: replace Abstract: Word Sense Disambiguation (WSD) has been widely evaluated using the semantic frameworks of WordNet, BabelNet, and the Oxford Dictionary of...
arXiv:2601.13327v2 Announce Type: replace Abstract: We present PepEDiff, a novel peptide binder generator that designs binding sequences given a target receptor protein sequence and its...
arXiv:2601.13350v2 Announce Type: replace Abstract: Distributional shifts between training and inference time data remain a central challenge in machine learning, often leading to poor performance....
arXiv:2601.14895v2 Announce Type: replace Abstract: We present SpatialMem, a memory-centric system for long-horizon, language-grounded retrieval and QA from egocentric video, where metric 3D serves as...
arXiv:2601.15160v3 Announce Type: replace Abstract: Large language models have achieved near-expert performance in structured reasoning domains like mathematics and programming, yet their ability to perform...