Stay updated with the latest research and technology news
arXiv:2601.10453v2 Announce Type: replace Abstract: Modal methods are a long-standing approach to physical modelling synthesis. Extensions to nonlinear problems are possible, leading to coupled nonlinear...
arXiv:2601.09173v3 Announce Type: replace Abstract: Analysis of learned representations has a blind spot: it focuses on $similarity$, measuring how closely embeddings align with external references,...
arXiv:2601.07348v5 Announce Type: replace Abstract: Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles, yet existing approaches suffer from low exploration efficiency, failing to discover...
arXiv:2601.05844v2 Announce Type: replace Abstract: Capturing fine-grained hand-object interactions is challenging due to severe self-occlusion from closely spaced fingers and the subtlety of in-hand manipulation...
arXiv:2601.04646v2 Announce Type: replace Abstract: Large-scale multi-tenant retrieval systems generate extensive query logs but lack curated relevance labels for effective domain adaptation, resulting in substantial...
arXiv:2601.04446v2 Announce Type: replace Abstract: We show that Inner Product in $2n$ variables, $\mathbf{IP}_n(x, y) = x_1y_1 \oplus \ldots \oplus x_ny_n$, can be computed by...
arXiv:2601.04058v2 Announce Type: replace Abstract: We address the problem of classifying trajectory data generated by some nonlinear dynamics, where each class corresponds to a distinct...
arXiv:2601.03192v2 Announce Type: replace Abstract: The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current...
arXiv:2601.03054v3 Announce Type: replace Abstract: Recent research on medical MLLMs has gradually shifted its focus from image-level understanding to fine-grained, pixel-level comprehension. Although segmentation serves...
arXiv:2601.01581v2 Announce Type: replace Abstract: The growth of Electric Vehicles (EVs) creates a conflict in vehicle-to-building (V2B) settings between building operators, who face high energy...
arXiv:2601.00768v2 Announce Type: replace Abstract: Despite much research, hard weighted problems still resist super-polynomial improvements over their textbook solution. On the other hand, the unweighted...
arXiv:2601.00668v2 Announce Type: replace Abstract: Spiking Neural Networks (SNNs) are dynamical systems that operate on spatiotemporal data, yet their learnable parameters are often limited to...
arXiv:2512.21561v2 Announce Type: replace Abstract: With the rapid development of quantum computing, classical cryptography systems are increasingly vulnerable to security threats, thereby highlighting the urgency...
arXiv:2512.20591v2 Announce Type: replace Abstract: Contact often occurs without macroscopic surface deformation, such as during interaction with liquids, semi-liquids, or ultra-soft materials. However, most existing...
arXiv:2512.19941v4 Announce Type: replace Abstract: As Vision Transformers (ViTs) become standard vision backbones, a mechanistic account of their computational phenomenology is essential. Despite architectural cues...
arXiv:2512.19905v2 Announce Type: replace Abstract: Recent developments in large language models have shown advantages in reallocating a notable share of computational resource from training time...
arXiv:2512.19269v2 Announce Type: replace Abstract: Recent advances in hierarchical robot systems leverage a high-level planner to propose task plans and a low-level policy to generate...
arXiv:2512.17663v3 Announce Type: replace Abstract: We study the computational complexity of scheduling jobs on a single speed-scalable processor with the objective of capturing the trade-off...
arXiv:2512.15926v3 Announce Type: replace Abstract: Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person...
arXiv:2512.15823v2 Announce Type: replace Abstract: Immersive formats such as 360{\deg} and 6DoF point cloud videos require high bandwidth and low latency, posing challenges for real-time...
arXiv:2512.13101v2 Announce Type: replace Abstract: Vision foundation models have demonstrated strong generalization in medical image segmentation by leveraging large-scale, heterogeneous pretraining. However, they often struggle...
arXiv:2512.12458v2 Announce Type: replace Abstract: Modern vector databases enable efficient retrieval over high-dimensional neural embeddings, powering applications from web search to retrieval-augmented generation. However, classical...
arXiv:2512.06562v2 Announce Type: replace Abstract: Recent advances in 3D-aware generative models have enabled high-fidelity image synthesis of human identities. However, this progress raises urgent questions...
arXiv:2512.05790v5 Announce Type: replace Abstract: We develop a theoretical framework that explains how gating mechanisms determine the learnability window $\mathcal{H}_N$ of recurrent neural networks, defined...