arXiv:2603.27467v1 Announce Type: new
Abstract: We compress KV cache entries by quantizing angles in the Fast Walsh-Hadamard domain, where a random diagonal rotation makes consecutive element pairs approximately uniformly distributed on the unit circl…
arXiv:2603.27420v1 Announce Type: cross
Abstract: Deep learning applications at the network edge lead to a significant growth in AI-related carbon emissions, presenting a critical sustainability challenge. The existing edge computing frameworks optimi…
arXiv:2603.27450v1 Announce Type: new
Abstract: Thanks to their remarkable flexibility, diffusion models and flow models have emerged as promising candidates for policy representation. However, efficient reinforcement learning (RL) upon these policies…
arXiv:2603.18532v2 Announce Type: replace-cross
Abstract: The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fine-tuning vision-language-action (VLA) models in ro…
arXiv:2603.27448v1 Announce Type: new
Abstract: Generating executable CAD programs from images requires alignment between visual geometry and symbolic program representations, a capability that current methods fail to learn reliably as design complexi…
arXiv:2603.01331v2 Announce Type: replace-cross
Abstract: Discrete diffusion language models (dLLMs) generate text by iteratively denoising a masked sequence. However, standard dLLMs condition each denoising step solely on the current hard-masked sequ…
arXiv:2603.27442v1 Announce Type: new
Abstract: When the system is linear, why should learning be nonlinear? Linear dynamical systems, the analytical backbone of control theory, signal processing and circuit analysis, have exact closed-form solutions …
arXiv:2602.04361v2 Announce Type: replace-cross
Abstract: Visual AutoRegressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction paradigm. However, mainstream VAR paradigms attend to all tokens across historic…
arXiv:2603.27432v1 Announce Type: new
Abstract: LayerNorm and RMSNorm impose fundamentally different geometric constraints on their outputs – and this difference has a precise, quantifiable consequence for model complexity. We prove that LayerNorm’s m…
arXiv:2512.09804v2 Announce Type: replace-cross
Abstract: This paper presents OnCoCo 1.0, a new public dataset for fine-grained message classification in online counseling. It is based on a new, integrative system of categories, designed to improve th…