arXiv:2603.15803v1 Announce Type: new Abstract: Discrete diffusion models offer global context awareness and flexible parallel generation. However, uniform random noise schedulers in standard DLLM training overlook the highly non-uniform information density inherent in real-world sequences. This wastes optimization resources on…
arXiv:2603.16749v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in applications with societal impact, raising concerns about the cultural biases they encode. We probe these representations by evaluating whether LLMs can perform author profiling from song lyrics…
arXiv:2603.15814v1 Announce Type: new Abstract: Breast cancer remains a leading cause of cancer-related mortality worldwide. Longitudinal mammography risk prediction models improve multi-year breast cancer risk prediction based on prior screening exams. However, in real-world clinical practice, longitudinal histories are often…
Fourth Power, founded by Professor Asegun Henry, is developing thermal batteries for efficiently storing excess electricity from utility grids and power producers.
arXiv:2603.15377v2 Announce Type: replace Abstract: Wider beam search should improve LLM reasoning, but when should you stop widening? Prior work on beam width selection has focused on inference efficiency citep{qin2025dsbd, freitag2017beam}, without analyzing whether wider search can emph{hurt} output quality.…
arXiv:2505.07272v2 Announce Type: replace-cross Abstract: Principal component analysis (PCA) is a key tool in the field of data dimensionality reduction. However, some applications involve heterogeneous data that vary in quality due to noise characteristics associated with each data sample. Heteroscedastic…
arXiv:2510.24318v4 Announce Type: replace Abstract: Bayesian clustering accounts for uncertainty but is computationally demanding at scale. Furthermore, real-world datasets often contain missing values, and simple imputation ignores the associated uncertainty, resulting in suboptimal results. We present Cluster-PFN, a Transformer-based model…
arXiv:2603.04427v2 Announce Type: replace Abstract: Standard transformer attention uses identical dimensionality for queries, keys, and values, yet these components serve different roles: queries and keys produce scalar attention weights (selection), while values carry rich representations (value transfer). We show that…
arXiv:2603.16866v1 Announce Type: cross Abstract: Learning in simulation provides a useful foundation for scaling robotic manipulation capabilities. However, this paradigm often suffers from a lack of data-generation-ready digital assets, in both scale and diversity. In this work, we present ManiTwin,…
arXiv:2505.20107v2 Announce Type: replace Abstract: Text-to-multiview (T2MV) diffusion models have shown great promise in generating multiple views of a scene from a single text prompt. While few-step backbones enable real-time T2MV generation, they often compromise key aspects of generation quality,…
