arXiv:2512.22245v1 Announce Type: new Abstract: As LLM-based judges become integral to industry applications, obtaining well-calibrated uncertainty estimates efficiently has become critical for production deployment. However, existing techniques, such as verbalized confidence and multi-generation methods, are often either poorly calibrated or…
arXiv:2512.20629v2 Announce Type: replace Abstract: This study proposes a multi-agent language framework that enables continual strategy evolution without fine-tuning the language model’s parameters. The core idea is to liberate the latent vectors of abstract concepts from traditional static semantic representations,…
arXiv:2512.22247v1 Announce Type: new Abstract: A systematic mismatch exists between mathematically ideal and effective activation updates during gradient descent. As intended, parameters update in their direction of steepest descent. However, activations are argued to constitute a more directly impactful quantity…
arXiv:2411.19466v2 Announce Type: replace-cross Abstract: Multimodal large language models have unlocked new possibilities for various multimodal tasks. However, their potential in image manipulation detection remains unexplored. When directly applied to the IMD task, M-LLMs often produce reasoning texts that suffer…
arXiv:2512.22248v1 Announce Type: new Abstract: Accurate prediction of model rocket flight performance requires estimating aerodynamic parameters that are difficult to measure directly. Traditional approaches rely on computational fluid dynamics or empirical correlations, while data-driven methods require extensive real flight data…
arXiv:2504.21491v2 Announce Type: replace-cross Abstract: We propose a result-level category-specific fusion architecture called ClassWise-CRF. This architecture employs a two-stage process: first, it selects expert networks that perform well in specific categories from a pool of candidate networks using a greedy…
arXiv:2512.22249v1 Announce Type: new Abstract: Unsupervised human motion segmentation (HMS) can be effectively achieved using subspace clustering techniques. However, traditional methods overlook the role of temporal semantic exploration in HMS. This paper explores the use of temporal vision semantics (TVS)…
arXiv:2509.09696v2 Announce Type: replace-cross Abstract: Higher-order brain connectivity (HOBC), which captures interactions among three or more brain regions, provides richer organizational information than traditional pairwise functional connectivity (FC). Recent studies have begun to infer latent HOBC from noninvasive imaging data,…
arXiv:2512.22251v1 Announce Type: new Abstract: Understanding how small molecules perturb gene expression is essential for uncovering drug mechanisms, predicting off-target effects, and identifying repurposing opportunities. While prior deep learning frameworks have integrated multimodal embeddings into biomedical knowledge graphs (BKGs) and…
arXiv:2512.19196v2 Announce Type: replace-cross Abstract: Solving high-dimensional Fokker-Planck (FP) equations is a challenge in computational physics and stochastic dynamics, due to the curse of dimensionality (CoD) and the bottleneck of evaluating second-order diffusion terms. Existing deep learning approaches, such as…
