Stay updated with the latest research and technology news
arXiv:2602.06639v1 Announce Type: new Abstract: The development of efficient and robust dynamic models is fundamental in the field of systems and control engineering. In this...
arXiv:2602.06643v1 Announce Type: new Abstract: Current approaches for humanoid whole-body manipulation, primarily relying on teleoperation or visual sim-to-real reinforcement learning, are hindered by hardware logistics...
arXiv:2602.06647v1 Announce Type: new Abstract: Spoken content, such as online videos and podcasts, often spans multiple topics, which makes automatic topic segmentation essential for user...
arXiv:2602.06650v1 Announce Type: new Abstract: Large Language Models (LLMs) face a fundamental safety-helpfulness trade-off due to static, one-size-fits-all safety policies that lack runtime controllabilityxf, making...
arXiv:2602.06652v1 Announce Type: new Abstract: The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable...
arXiv:2602.06653v1 Announce Type: new Abstract: Developing robotic manipulation policies is iterative and hypothesis-driven: researchers test tactile sensing, gripper geometries, and sensor placements through real-world data...
arXiv:2602.06654v1 Announce Type: new Abstract: Multimodal retrieval models are becoming increasingly important in scenarios such as food delivery, where rich multimodal features can meet diverse...
arXiv:2602.06655v1 Announce Type: new Abstract: Over the last years, Ethereum has evolved into a public platform that safeguards the savings of hundreds of millions of...
arXiv:2602.06658v1 Announce Type: new Abstract: A fundamental challenge in data science is to match disparate point sets with each other. While optimal transport efficiently minimizes...
arXiv:2602.06663v1 Announce Type: new Abstract: Unified multimodal models (UMMs) have shown impressive capabilities in generating natural images and supporting multimodal reasoning. However, their potential in...
arXiv:2602.06665v1 Announce Type: new Abstract: Post-training improves instruction-following and helpfulness of large language models (LLMs) but often reduces generation diversity, which leads to repetitive outputs...
arXiv:2602.06669v1 Announce Type: new Abstract: Large Language Models (LLMs) often show reduced performance, cultural alignment, and safety robustness in non-English languages, partly because English dominates...
arXiv:2602.06671v1 Announce Type: new Abstract: Summarizing source code into natural language descriptions (code summarization) helps developers better understand program functionality and reduce the burden of...
arXiv:2602.06674v1 Announce Type: new Abstract: High-quality annotated datasets are crucial for advancing machine learning in medical image analysis. However, a critical gap exists: most datasets...
arXiv:2602.06675v1 Announce Type: new Abstract: Pruning at Initialisation methods discover sparse, trainable subnetworks before training, but their theoretical mechanisms remain elusive. Existing analyses are often...
arXiv:2602.06676v1 Announce Type: new Abstract: Fake Image Detection (FID), aiming at unified detection across four image forensic subdomains, is critical in real-world forensic scenarios. Compared...
arXiv:2602.06677v1 Announce Type: new Abstract: We analyze the Double Fourier Sphere (DFS) method on the rotation group $\mathcal{SO}(3)$ in the frequency domain and demonstrate its...
arXiv:2602.06678v1 Announce Type: new Abstract: In the age of Large Language Models (LLMs), much work has already been done on how LLMs support medication advice...
arXiv:2602.06680v1 Announce Type: new Abstract: Fixpoint iteration constitutes the algorithmic core of static analyzers. Parallelizing the fixpoint engine can significantly reduce analysis times. Previous approaches...
arXiv:2602.06685v1 Announce Type: new Abstract: We study a family of Laguerre--Sobolev orthogonal polynomials associated with a Sobolev inner product arising from second--order boundary value problems...
arXiv:2602.06687v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable proficiency in vulnerability detection. However, a critical reliability gap persists: models frequently yield...
arXiv:2602.06689v1 Announce Type: new Abstract: Autoregressive generative PDE solvers can be accurate one step ahead yet drift over long rollouts, especially in coarse-to-fine regimes where...
arXiv:2602.06692v1 Announce Type: new Abstract: The groundbreaking capabilities of Large Language Models (LLMs) offer new opportunities for enhancing human-computer interaction through emotion-adaptive Artificial Intelligence (AI)....
arXiv:2602.06693v1 Announce Type: new Abstract: Split learning recently emerged as a solution for distributed machine learning with heterogeneous IoT devices, where clients can offload part...