arXiv:2511.21675v1 Announce Type: cross Abstract: Causal effect estimation in networked systems is central to data-driven decision making. In such settings, interventions on one unit can spill over to others, and in complex physical or social systems, the interaction pathways driving…
arXiv:2511.20913v1 Announce Type: new Abstract: Existing studies on reinforcement learning (RL) for sepsis management have mostly followed an established problem setup, in which patient data are aggregated into 4-hour time steps. Although concerns have been raised regarding the coarseness of…
arXiv:2402.03589v2 Announce Type: replace Abstract: Bike-sharing systems (BSS) provide a sustainable urban mobility solution, but ensuring their reliability requires effective rebalancing strategies to address stochastic demand and prevent station imbalances. This paper proposes reinforcement learning (RL) algorithms for dynamic rebalancing…
arXiv:2511.20927v1 Announce Type: new Abstract: Recent theoretical work established the unsupervised identifiability of quantized factors under any diffeomorphism. The theory assumes that quantization thresholds correspond to axis-aligned discontinuities in the probability density of the latent factors. By constraining a learned…
arXiv:2409.17264v5 Announce Type: replace Abstract: Deploying million-token Large Language Models (LLMs) is challenging because production workloads are highly heterogeneous, mixing short queries and long documents. This heterogeneity, combined with the quadratic complexity of attention, creates severe convoy effects where long-running…
arXiv:2511.20944v1 Announce Type: new Abstract: Business Email Compromise (BEC) is a sophisticated social engineering threat that manipulates organizational hierarchies and exploits psychological vulnerabilities, leading to significant financial damage. According to the 2024 FBI Internet Crime Report, BEC accounts for over…
arXiv:2503.21507v2 Announce Type: replace Abstract: Implicit Neural Representations (INRs) model signals as continuous, differentiable functions. However, monolithic INRs scale poorly with data dimensionality, leading to excessive training costs. We propose F-INR, a framework that addresses this limitation by factorizing a…
arXiv:2511.20992v1 Announce Type: new Abstract: Behavior Cloning (BC) is a popular framework for training sequential decision policies from expert demonstrations via supervised learning. As these policies are increasingly being deployed in the real world, their robustness and potential vulnerabilities are…
arXiv:2506.00299v2 Announce Type: replace Abstract: Diffusion models are state-of-the-art generative models, yet their samples often fail to satisfy application objectives such as safety constraints or domain-specific validity. Existing techniques for alignment require gradients, internal model access, or large computational budgets…
arXiv:2511.20993v1 Announce Type: new Abstract: Large language models (LLMs) offer strong high-level planning capabilities for reinforcement learning (RL) by decomposing tasks into subgoals. However, their practical utility is limited by poor planning-execution alignment, which reflects a critical gap between abstract…
