Stay updated with the latest research and technology news
arXiv:2511.07222v2 Announce Type: replace Abstract: This paper presents Omni-View, which extends the unified multimodal understanding and generation to 3D scenes based on multiview images, exploring...
arXiv:2511.07888v2 Announce Type: replace Abstract: A persistent challenge in text classification (TC) is that enhancing model robustness against adversarial attacks typically degrades performance on clean...
arXiv:2511.07994v3 Announce Type: replace Abstract: Graph neural networks (GNNs) can effectively model structural information of graphs, making them widely used in knowledge graph (KG) reasoning....
arXiv:2511.09139v2 Announce Type: replace Abstract: Hundreds of benchmarks dedicated to evaluating large models have been presented over the past few years. However, most of them...
arXiv:2511.09529v3 Announce Type: replace Abstract: Structure-based drug design (SBDD) faces a fundamental scaling fidelity dilemma: rich pocket-aware conditioning captures interaction geometry but can be costly,...
arXiv:2511.09907v4 Announce Type: replace Abstract: Data synthesis for training large reasoning models offers a scalable alternative to limited, human-curated datasets, enabling the creation of high-quality...
arXiv:2511.10691v2 Announce Type: replace Abstract: The potential data contamination issue in contemporary large language models (LLMs) benchmarks presents a fundamental challenge to establishing trustworthy evaluation...
arXiv:2511.10840v2 Announce Type: replace Abstract: Multilingual Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear. Do they...
arXiv:2511.12055v4 Announce Type: replace Abstract: In this work, we propose data-integrated neural networks (DataInNet) for solving partial differential equations (PDEs), offering a novel approach to...
arXiv:2511.13725v3 Announce Type: replace Abstract: Recently, web-based Large Language Model (LLM) agents autonomously perform increasingly complex tasks, thereby bringing significant convenience. However, they also amplify...
arXiv:2511.14109v2 Announce Type: replace Abstract: Visual Place Recognition (VPR) aims to match query images against a database using visual cues. State-of-the-art methods aggregate features from...
arXiv:2511.16377v2 Announce Type: replace Abstract: We investigate how to optimally design local differential privacy (LDP) mechanisms that reduce data unfairness and thereby improve fairness in...
arXiv:2511.17100v3 Announce Type: replace Abstract: Large language models (LLMs) can internalize private or harmful content, motivating unlearning that removes a forget set while preserving retaining...
arXiv:2511.17961v2 Announce Type: replace Abstract: Constructing photorealistic and controllable robotic arm digital assets from real observations is fundamental to robotic applications. Current approaches naively bind...
arXiv:2511.18616v2 Announce Type: replace Abstract: Beliefs shape how people reason, communicate, and behave. Rather than existing in isolation, they exhibit a rich correlational structure--some connected...
arXiv:2511.20102v2 Announce Type: replace Abstract: Sparse attention reduces the quadratic complexity of full self-attention but faces two challenges: (1) an attention gap, where applying sparse...
arXiv:2511.20275v4 Announce Type: replace Abstract: Reinforcement learning (RL) controllers have made impressive progress in humanoid locomotion and light-weight object manipulation. However, achieving robust and precise...
arXiv:2511.20922v3 Announce Type: replace Abstract: Quantum machine learning (QML) promises compact and expressive representations, but suffers from the measurement bottleneck - a narrow quantum-to-classical readout...
arXiv:2511.21211v2 Announce Type: replace Abstract: Gene prioritization (identifying genes potentially associated with a biological process) is increasingly tackled with Artificial Intelligence. However, existing methods struggle...
arXiv:2511.21322v2 Announce Type: replace Abstract: Millions of users across the globe turn to AI chatbots for their creative needs, inviting widespread interest in understanding how...
arXiv:2512.00985v2 Announce Type: replace Abstract: Links in practical systems, such as satellite--terrestrial integrated networks, exhibit distinct delay distributions, intermittent availability, and heterogeneous energy costs. These...
arXiv:2512.00986v2 Announce Type: replace Abstract: A surge in academic publications calls for automated deep research (DR) systems, but accurately evaluating them is still an open...
arXiv:2512.01017v3 Announce Type: replace Abstract: Recent advances in multimodal large language models (MLLMs) highlight the need for benchmarks that rigorously evaluate structured chart comprehension. Chart...
arXiv:2512.01372v3 Announce Type: replace Abstract: Multimodal recommendation aims to integrate collaborative signals with heterogeneous content such as visual and textual information, but remains challenged by...