arXiv:2604.22891v1 Announce Type: new Abstract: LLM-as-a-Judge has become a dominant approach in automated evaluation systems, playing critical roles in model alignment, leaderboard construction, quality control, and so on. However, the scalability and trustworthiness of this approach can be substantially distorted…
arXiv:2603.03269v2 Announce Type: replace-cross Abstract: Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or limited effective memory in recurrent designs. We present LoGeR (Long-context Geometric Reconstruction), a novel…
arXiv:2604.22892v1 Announce Type: new Abstract: Feature selection in high-dimensional genomic data ($d gg n$) demands methods that are simultaneously accurate, sparse, and stable. Existing approaches either require manual threshold specification (mRMR, stability selection), produce unstable selections under data perturbation (Lasso,…
arXiv:2604.23647v1 Announce Type: cross Abstract: In Transformer models, non-GEMM (non-General Matrix Multiplication) operations — especially Softmax and Layer Normalization (LayerNorm) — often dominate hardware cost due to their nonlinear nature. To address this, previous approximation studies mainly target rank-oriented tasks,…
arXiv:2604.22893v1 Announce Type: new Abstract: Traditional data valuation methods based on “row-count $times$ quality coefficient” paradigms fail to capture the nuanced, nonlinear contributions that data makes to Large Language Model (LLM) capabilities. This paper presents a dynamic data valuation framework…
arXiv:2604.23944v1 Announce Type: cross Abstract: We propose a new regularized optimal transport (OT) formulation, termed sliced-regularized optimal transport (SROT). Unlike entropic OT (EOT), which regularizes the transport plan toward an independent coupling, SROT regularizes it toward a smoothened sliced OT…
arXiv:2604.22901v1 Announce Type: new Abstract: Diffusion models achieve remarkable success in time series generation. However, slow inference limits their practical deployment. We propose E$^2$-CRF (Error-Feedback Event-Driven Cumulative Residual Feature caching) to accelerate frequency domain diffusion models. Our method exploits two…
arXiv:2604.24397v1 Announce Type: cross Abstract: In the noisy intermediate-scale quantum (NISQ) regime, quantum devices contain hardware-specific noise sources which restrict device-invariant error mitigation strategies. We explore transfer learning approaches to apply noise models learned on one quantum device to a…
arXiv:2604.22909v1 Announce Type: new Abstract: Understanding and representing complex climate variability is essential for both scientific analysis and predictive modeling. However, identifying meaningful climate regimes from raw variables is challenging, as they exhibit high noise and nonlinear dependencies. In this…
arXiv:2604.24668v1 Announce Type: cross Abstract: Given the increased use of LLMs in financial systems today, it becomes important to evaluate the safety and robustness of such systems. One failure mode that LLMs frequently display in general domain settings is that…
