arXiv:2603.25047v1 Announce Type: cross Abstract: In a controlled experiment on modular arithmetic ($p = 9973$), varying only example ordering while holding all else constant, two fixed-ordering strategies achieve 99.5% test accuracy by epochs 487 and 659 respectively from a training set comprising 0.3% of the input space, well below established sample complexity lower bounds for this task under IID ordering. The IID baseline achieves 0.30% after 5{,}000 epochs from identical data. An adversarially structured ordering suppresses learning entirely. […]

Ver mais

Integer sequences in the OEIS span values from single-digit constants to astronomical factorials and exponentials, making prediction challenging for standard tokenised models that cannot handle out-of-vocabulary values or exploit periodic arithmetic structure. We present IntSeqBERT, a dual-stream Transformer encoder for masked integer-sequence modelling on OEIS. Each sequence element is encoded along two complementary axes: a continuous log-scale magnitude embedding and sin/cos modulo embeddings for 100 residues (moduli $2$–$101$), fused via FiLM. Three prediction heads (magnitude regression, sign classification, […]

Ver mais

Unmanned aerial vehicles (UAVs) are increasingly used to support time-critical medical supply delivery, providing rapid and flexible logistics during emergencies and resource shortages. However, effective deployment of UAV fleets requires coordination mechanisms capable of prioritizing medical requests, allocating limited aerial resources, and adapting delivery schedules under uncertain operational conditions. This paper presents a multi-agent reinforcement learning (MARL) framework for coordinating UAV fleets in stochastic medical delivery scenarios where requests vary in urgency, location, and delivery deadlines. The problem […]

Ver mais

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key approach for enhancing LLM reasoning.However, standard frameworks like Group Relative Policy Optimization (GRPO) typically employ a uniform rollout budget, leading to resource inefficiency. Moreover, existing adaptive methods often rely on instance-level metrics, such as task pass rates, failing to capture the model’s dynamic learning state. To address these limitations, we propose CoBA-RL, a reinforcement learning algorithm designed to adaptively allocate rollout budgets based on the model’s evolving […]

Ver mais

arXiv:2601.22264v1 Announce Type: new Abstract: In principle, Continuous Integration (CI) pipeline failures provide valuable feedback to developers on code-related errors. In practice, however, pipeline jobs often fail intermittently due to non-deterministic tests, network outages, infrastructure failures, resource exhaustion, and other reliability issues. These intermittent (flaky) job failures lead to substantial inefficiencies: wasted computational resources from repeated reruns and significant diagnosis time that distracts developers from core activities and often requires intervention from specialized teams. Prior work has proposed […]

Ver mais

Safe Reinforcement Learning (RL) is crucial for achieving high performance while ensuring safety in real-world applications. However, the complex interplay of multiple uncertainty sources in real environments poses significant challenges for interpretable risk assessment and robust decision-making. To address these challenges, we propose Fuz-RL, a fuzzy measure-guided robust framework for safe RL. Specifically, our framework develops a novel fuzzy Bellman operator for estimating robust value functions using Choquet integrals. Theoretically, we prove that solving the Fuz-RL problem (in […]

Ver mais

arXiv:2601.02387v1 Announce Type: new Abstract: Satellite networks with wide coverage are considered natural extensions to terrestrial networks for their long-distance end-to-end (E2E) service provisioning. However, the inherent topology dynamics of low earth orbit satellite networks and the uncertain network scales bring an inevitable requirement that resource chains for E2E service provisioning must be efficiently re-planned. Therefore, achieving highly adaptive resource management is of great significance in practical deployment applications. This paper first designs a regional resource management (RRM) […]

Ver mais

arXiv:2602.18466v1 Announce Type: new Abstract: K-12 science classrooms are rich sites of inquiry where students coordinate phenomena, evidence, and explanatory models through discourse; yet, the multimodal complexity of these interactions has made automated analysis elusive. Existing benchmarks for classroom discourse focus primarily on mathematics and rely solely on transcripts, overlooking the visual artifacts and model-based reasoning emphasized by the Next Generation Science Standards (NGSS). We address this gap with SciIBI, the first video benchmark for analyzing science classroom […]

Ver mais

A complete walkthrough of implementing the original Attention Is All You Need encoder-decoder Transformer—no torch. nn.Transformer, no shortcuts. The 2017 paper “Attention Is All You Need” by Vaswani et al. fundamentally changed natural language processing by replacing recurrent networks with a purely attention-based architecture . Yet for most practitioners, the Transformer remains a black box—something you import from Hugging Face and fine-tune. This article walks through a full from-scratch PyTorch implementation of the original encoder-decoder Transformer, inspired by the Harvard […]

Ver mais