Reinforcement learning (RL) has shown promising results in active flow control (AFC), yet progress in the field remains difficult to assess as existing studies rely on heterogeneous observation and actuation schemes, numerical setups, and evaluation protocols. Current AFC benchmarks attempt to address these issues but heavily rely on external computational fluid dynamics (CFD) solvers, are not fully differentiable, and provide limited 3D and multi-agent support. To overcome these limitations, we introduce FluidGym, the first standalone, fully differentiable benchmark […]

Ver mais

arXiv:2604.05072v1 Announce Type: new Abstract: Recent large language models have shifted SVG generation from differentiable rendering optimization to autoregressive program synthesis. However, existing approaches still rely on generic byte-level tokenization inherited from natural language processing, which poorly reflects the geometric structure of vector graphics. Numerical coordinates are fragmented into discrete symbols, destroying spatial relationships and introducing severe token redundancy, often leading to coordinate hallucination and inefficient long-sequence generation. To address these challenges, we propose HiVG, a hierarchical SVG […]

Ver mais

arXiv:2602.15161v1 Announce Type: new Abstract: Federated learning (FL) enables distributed model training across edge devices while preserving data locality. This decentralized approach has emerged as a promising solution for collaborative learning on sensitive user data, effectively addressing the longstanding privacy concerns inherent in centralized systems. However, the decentralized nature of FL exposes new security vulnerabilities, especially backdoor attacks that threaten model integrity. To investigate this critical concern, this paper presents the Layer Smoothing Attack (LSA), a novel backdoor […]

Ver mais

Deploying RL agents on real physical hardware often reveals a catastrophic flaw: hardware drift. I built MicroSafe-RL to act as a real-time safety interceptor that constrains the action space based on hardware stability signatures. Universal Gym Wrapper: I’ve added a MicroSafeWrapper that allows you to apply the same safety shielding and reward shaping during simulation that you will use on the actual hardware. Reward Shaping: The wrapper uses a safety signal to penalize entropy and “Chaos” states, helping […]

Ver mais

arXiv:2604.00848v2 Announce Type: replace-cross Abstract: High-dimensional statistical settings ($p gg n$) pose fundamental challenges for classical inference, largely due to bias introduced by regularized estimators such as the LASSO. To address this, Javanmard and Montanari (2014) propose a debiased estimator that enables valid hypothesis testing and confidence interval construction. This report examines their debiased LASSO framework, which yields asymptotically normal estimators in high-dimensional settings. The key theoretical results underlying this approach are presented. Specifically, the construction of an […]

Ver mais

arXiv:2604.08551v1 Announce Type: new Abstract: We investigate the emerging prospect of self-sovereign agents — AI systems that can economically sustain and extend their own operation without human involvement. Recent advances in large language models and agent frameworks have substantially expanded agents’ practical capabilities, pointing toward a potential shift from developer-controlled tools to more autonomous digital actors. We analyze the remaining technical barriers to such deployments and discuss the security, societal, and governance challenges that could arise if such […]

Ver mais

Soft robotic grippers excel in unstructured manipulation but suffer catastrophic failure rates (72%) when grasping deformable organics, fabrics, and mixed debris due to hyperchaotic pneumatic dynamics. This paper introduces the first Lyapunov stability controller for soft robotics, deploying real-time maximal Lyapunov exponent estimation (λ_MLE) from fibre-optic strain sensor arrays running at 100Hz on Intel Loihi 2 neuromorphic chips. The system reconstructs 12D phase space embeddings via Takens theorem, detecting chaos onset 187ms early during dual-material transitions (tomato → […]

Ver mais

What if you could hold a hedge fund position and still trade its liquidity on a public blockchain at 3 a.m. on a Sunday? That is the question Tok-Edge, a London-based digital asset firm, is putting in front of institutional allocators with the launch of what it calls the Redemption Token, confirmed on April 7, 2026 at a $15 million company valuation. The firm raised roughly $1.5 million in its pre-launch round, led by Marcus Meijer, founder of […]

Ver mais

arXiv:2601.13776v1 Announce Type: cross Abstract: Orthogonal and 1-Lipschitz neural network layers are essential building blocks in robust deep learning architectures, crucial for certified adversarial robustness, stable generative models, and reliable recurrent networks. Despite significant advancements, existing implementations remain fragmented, limited, and computationally demanding. To address these issues, we introduce Orthogonium , a unified, efficient, and comprehensive PyTorch library providing orthogonal and 1-Lipschitz layers. Orthogonium provides access to standard convolution features-including support for strides, dilation, grouping, and transposed-while maintaining […]

Ver mais

arXiv:2603.25916v1 Announce Type: cross Abstract: We study dynamic regret minimization in unconstrained adversarial linear bandit problems. In this setting, a learner must minimize the cumulative loss relative to an arbitrary sequence of comparators $boldsymbol{u}_1,ldots,boldsymbol{u}_T$ in $mathbb{R}^d$, but receives only point-evaluation feedback on each round. We provide a simple approach to combining the guarantees of several bandit algorithms, allowing us to optimally adapt to the number of switches $S_T = sum_tmathbb{I}{boldsymbol{u}_t neq boldsymbol{u}_{t-1}}$ of an arbitrary comparator sequence. In […]

Ver mais