Quality follows upgrading
Academic
arXiv:2603.17353v1 Announce Type: new Abstract: The finite symmetric group S_n provides a natural domain for permutations, yet learning probability distributions on S_n is challenging due …
arXiv:2603.17354v1 Announce Type: new Abstract: Layer-wise mixed-precision quantization (LMPQ) enables effective compression under extreme low-bit settings by allocating higher precision to sensitive layers. However, existing …
arXiv:2603.17365v1 Announce Type: new Abstract: Internal noise in deep networks is usually inherited from heuristics such as dropout, hard masking, or additive perturbation. We ask …
arXiv:2603.17378v1 Announce Type: new Abstract: We develop an online learning algorithm that dramatically improves the data efficiency of reinforcement learning from human feedback (RLHF). Our …
arXiv:2603.17380v1 Announce Type: new Abstract: Virtual cell models aim to enable in silico experimentation by predicting how cells respond to genetic, chemical, or cytokine perturbations …
arXiv:2603.17384v1 Announce Type: new Abstract: Current continuous generative models (e.g., Diffusion Models, Flow Matching) implicitly assume that locally consistent causal mechanisms naturally yield globally coherent …
arXiv:2603.17385v1 Announce Type: new Abstract: Judea Pearl's do-calculus provides a foundation for causal inference, but its translation to continuous generative models remains fraught with geometric …
arXiv:2603.17403v1 Announce Type: new Abstract: Earthquake hazard analysis and design of spatially distributed infrastructure, such as power grids and energy pipeline networks, require scenario-specific ground-motion …
arXiv:2603.17405v1 Announce Type: new Abstract: Causal representation learning (CRL) models aim to transform high-dimensional data into a latent space, enabling interventions to generate counterfactual samples …
arXiv:2603.17433v1 Announce Type: new Abstract: Transformer models have redefined sequence learning, yet dot-product self-attention introduces a quadratic token-mixing bottleneck for long-context time-series. We introduce the …
arXiv:2603.17436v1 Announce Type: new Abstract: Non-stationarity is a fundamental challenge in multivariate long-term time series forecasting, often manifested as rapid changes in amplitude and phase. …
arXiv:2603.17439v1 Announce Type: new Abstract: Transformers enable in-context learning (ICL) for rapid, gradient-free adaptation in time series forecasting, yet most ICL-style approaches rely on tabularized, …
