Effective decision-making in the real world depends on memory that is both stable and adaptive: environments change over time, and agents must retain relevant information over long horizons while also updating or overwriting outdated content when circumstances shift. Existing Reinforcement Learning (RL) benchmarks and memory-augmented agents focus primarily on retention, leaving the equally critical ability of memory rewriting largely unexplored. To address this gap, we introduce a benchmark that explicitly tests continual memory updating under partial observability, i.e. […]

Ver mais

We develop a geometric and combinatorial framework for the distinct-prime Goldbach conjecture—the assertion that every even integer $2N geq 8$ is the sum of two distinct primes. The framework rests on three components: (1) a novel geometric equivalence reformulating the problem in terms of nested squares with semiprime areas, (2) a rigorous combinatorial reduction to a set intersection condition on prime-pair half-differences, and (3) a complementary conditional argument supported by computation. The geometric construction reveals that the conjecture […]

Ver mais

Accurate estimation of aerodynamic state variables such as freestream velocity and angle of attack (AoA) is important for aerodynamic load prediction, flight control, and model validation. This work presents a non-intrusive method for estimating vehicle velocity and AoA from structural vibration measurements rather than direct flow instrumentation such as pitot tubes. A dense array of piezoelectric sensors mounted on the interior skin of an aeroshell capture vibrations induced by turbulent boundary layer pressure fluctuations, and a convolutional neural […]

Ver mais

Hi I’ll just leave this here for you guys to check out. It is llama.cpp with PrimeVHT2 integration which is like TurboQuant except it is working and better! reaching the maximum at 0.9987. One is pure llama.cpp with PrimeVHT2 and the other is llama-turbo with PrimeVHT2. PrimeVHT2 is the basis for the unrelease llama.cpp turbo algorithm https://github.com/nihilistau/llama-cpp-vht2 https://github.com/nihilistau/llama-PrimeVHT2 # PrimePE / Position_Is_Arithmetic — Session Context v3 ## Date: April 5, 2026 | Updated: VHT2 banded compression validated + […]

Ver mais

arXiv:2306.13681v3 Announce Type: replace-cross Abstract: In an era of data abundance, statistical evidence is increasingly critical for business and policy decisions. Yet, organizations lack empirical tools to assess the value of evidence-based decision making (EBDM), optimize statistical precision, and balance the costs of evidence-gathering strategies against their benefits. To tackle these challenges, this article introduces an empirical framework to estimate the value of EBDM and evaluate the return on investment in statistical precision and project ideation. The framework […]

Ver mais

Autonomous navigation in highly constrained environments remains challenging for mobile robots. Classical navigation approaches offer safety assurances but require environment-specific parameter tuning; end-to-end learning bypasses parameter tuning but struggles with precise control in constrained spaces. To this end, recent robot learning approaches automate parameter tuning while retaining classical systems’ safety, yet still face challenges in generalizing to unseen environments. Recently, Vision-Language-Action (VLA) models have shown promise by leveraging foundation models’ scene understanding capabilities, but still struggle with precise […]

Ver mais

arXiv:2602.10286v1 Announce Type: new Abstract: Pairwise preference learning is central to machine learning, with recent applications in aligning language models with human preferences. A typical dataset consists of triplets $(x, y^+, y^-)$, where response $y^+$ is preferred over response $y^-$ for context $x$. The Bradley–Terry (BT) model is the predominant approach, modeling preference probabilities as a function of latent score differences. Standard practice assumes data follows this model and learns the latent scores accordingly. However, real data may […]

Ver mais

arXiv:2603.17056v1 Announce Type: new Abstract: Reliable terrain perception is a fundamental requirement for autonomous navigation in unstructured, off-road environments. Desert landscapes present unique challenges due to low chromatic contrast between terrain categories, extreme lighting variability, and sparse vegetation that defy the assumptions of standard road-scene segmentation models. We present DesertFormer, a semantic segmentation pipeline for off-road desert terrain analysis based on SegFormer B2 with a hierarchical Mix Transformer (MiT-B2) backbone. The system classifies terrain into ten ecologically meaningful […]

Ver mais

Multimodal learning enables neural networks to integrate information from heterogeneous sources, but active learning in this setting faces distinct challenges. These include missing modalities, differences in modality difficulty, and varying interaction structures. These are issues absent in the unimodal case. While the behavior of active learning strategies in unimodal settings is well characterized, their behavior under such multimodal conditions remains poorly understood. We introduce a new framework for benchmarking multimodal active learning that isolates these pitfalls using synthetic […]

Ver mais