arXiv:2603.10030v1 Announce Type: new Abstract: AI transport libraries move bytes efficiently, but they commonly assume that buffers are already correctly allocated, placed, shared, registered, and safe under completion and teardown pressure. This paper presents dmaplane, a Linux kernel module that makes this missing layer explicit as buffer orchestration. dmaplane exposes a stable kernel UAPI via /dev/dmaplane and composes ring-based command channels, DMA buffer lifecycle management, dma-buf export for cross-device sharing, a kernel-space RDMA engine, NUMA-aware allocation and verification, […]

Ver mais

arXiv:2601.18930v1 Announce Type: new Abstract: We are interested in enabling autonomous agents to learn and reason about systems with hidden states, such as furniture with hidden locking mechanisms. We cast this problem as learning the parameters of a discrete Partially Observable Markov Decision Process (POMDP). The agent begins with knowledge of the POMDP’s actions and observation spaces, but not its state space, transitions, or observation models. These properties must be constructed from action-observation sequences. Spectral approaches to learning […]

Ver mais

Last week, BBC journalist Thomas Germain wrote a fake blog post claiming he was the world’s greatest hot-dog-eating tech journalist. Within 24 hours, ChatGPT and Google were repeating it as fact. Claude, made by Anthropic, wasn’t fooled. One AI out of three caught the lie. The entire industry treated that as an interesting footnote. An engineer would call it the most important finding in the article. Two Inspectors Approved a Defective Part I am 75 years old. I […]

Ver mais

arXiv:2603.21393v1 Announce Type: cross Abstract: The widespread use of AI and ML models in sensitive areas raises significant concerns about fairness. While the research community has introduced various methods for bias mitigation in binary classification tasks, the issue remains under-explored in multi-class classification settings. To address this limitation, in this paper, we first formulate the problem of fair learning in multi-class classification as a multi-objective problem between effectiveness (i.e., prediction correctness) and multiple linear fairness constraints. Next, we […]

Ver mais

Ensemble learning is a well established body of methods for machine learning to enhance predictive performance by combining multiple algorithms/models. Combinatorial Fusion Analysis (CFA) has provided method and practice for combining multiple scoring systems, using rank-score characteristic (RSC) function and cognitive diversity (CD), including ensemble method and model fusion. However, there is no general-purpose Python tool available that incorporate these techniques. In this paper we introduce texttt{InFusionLayer}, a machine learning architecture inspired by CFA at the system fusion […]

Ver mais

arXiv:2602.03893v1 Announce Type: new Abstract: Although the iterative reconstruction (IR) algorithm can substantially correct reconstruction artifacts in photoacoustic (PA) computed tomography (PACT), it suffers from long reconstruction times, especially for large-scale three-dimensional (3D) imaging in which IR takes hundreds of seconds to hours. The computing burden severely limits the practical applicability of IR algorithms. In this work, we proposed an ultrafast IR method for 3D PACT, called Gaussian-kernel-based Ultrafast 3D Photoacoustic Iterative Reconstruction (GPAIR), which achieves orders-of-magnitude acceleration […]

Ver mais

arXiv:2601.09173v4 Announce Type: replace-cross Abstract: Representational similarity analysis and related methods have become standard tools for comparing the internal geometries of neural networks and biological systems. These methods measure what is represented, the alignment between two representational spaces, but not whether that structure is robust. We introduce geometric stability, a distinct dimension of representational quality that quantifies how reliably a representation’s pairwise distance structure holds under perturbation. Our metric, Shesha, measures self-consistency through split-half correlation of representational dissimilarity […]

Ver mais

Model-based offline reinforcement learning (RL) aims to enhance offline RL with a dynamics model that facilitates policy exploration. However, textit{model exploitation} could occur due to inevitable model errors, degrading algorithm performance. Adversarial model learning offers a theoretical framework to mitigate model exploitation by solving a maximin formulation. Within such a paradigm, RAMBO~citep{rigter2022rambo} has emerged as a representative and most popular method that provides a practical implementation with model gradient. However, we empirically reveal that severe Q-value underestimation and […]

Ver mais

arXiv:2602.21221v1 Announce Type: new Abstract: Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, which incurs prohibitive synthetic data costs and requires modifying model weights, creating stateful parameters that complicate concurrent serving. We propose Latent Context Compilation, a framework that fundamentally shifts context processing from adaptation to compilation. By utilizing a disposable LoRA module as a compiler, we distill long contexts into compact buffer tokens — stateless, […]

Ver mais