This paper presents a deep reinforcement learning (DRL) based controller for collective navigation of unmanned aerial vehicle (UAV) swarms in communication-denied environments, enabling robust operation in complex, obstacle-rich environments. Inspired by biological swarms where informed individuals guide groups without explicit communication, we employ an implicit leader-follower framework. In this paradigm, only the leader possesses goal information, while follower UAVs learn robust policies using only onboard LiDAR sensing, without requiring any inter-agent communication or leader identification. Our system utilizes […]

Ver mais

arXiv:2502.01557v3 Announce Type: replace-cross Abstract: Despite exceptional achievements, training neural networks remains computationally expensive and is often plagued by instabilities that can degrade convergence. While learning rate schedules can help mitigate these issues, finding optimal schedules is time-consuming and resource-intensive. This work explores theoretical issues concerning training stability in the constant-learning-rate (i.e., without schedule) and small-batch-size regime. Surprisingly, we show that the composition order of gradient updates affects stability and convergence in gradient-based optimizers. We illustrate this new […]

Ver mais

On March 31, 2026, two research papers dropped on the same day and rewrote everything we thought we knew about Bitcoin’s quantum timeline. Google’s Quantum AI team, alongside researchers from Stanford and the Ethereum Foundation, published findings showing that breaking Bitcoin’s ECDSA encryption could require fewer than 500,000 physical qubits — a roughly 20-fold reduction from prior estimates that hovered in the millions. The same day, a Caltech/Oratomic paper demonstrated that neutral-atom architectures could push that number even […]

Ver mais

arXiv:2601.17067v1 Announce Type: new Abstract: Large-scale video generation models have demonstrated emergent physical coherence, positioning them as potential world models. However, a gap remains between contemporary “stateless” video architectures and classic state-centric world model theories. This work bridges this gap by proposing a novel taxonomy centered on two pillars: State Construction and Dynamics Modeling. We categorize state construction into implicit paradigms (context management) and explicit paradigms (latent compression), while dynamics modeling is analyzed through knowledge integration and architectural […]

Ver mais

arXiv:2601.09720v1 Announce Type: new Abstract: Question answering (QA) systems are increasingly deployed across domains. However, their reliability is undermined when retrieved evidence is incomplete, noisy, or uncertain. Existing knowledge graph (KG) based QA frameworks typically represent facts as static and deterministic, failing to capture the evolving nature of information and the uncertainty inherent in reasoning. We present a demonstration of uncertainty-aware dynamic KGs, a framework that combines (i) dynamic construction of evolving KGs, (ii) confidence scoring and uncertainty-aware […]

Ver mais

For people just starting out in GPU kernel engineering or LLM inference (FlashAttention / FlashInfer / SGLang / vLLM style work), most job postings still list “C++17, CuTe, CUTLASS” as hard requirements. At the same time NVIDIA has been pushing CuTeDSL (the Python DSL in CUTLASS 4.x) hard since late 2025 as the new recommended path for new kernels — same performance, no template metaprogramming, JIT, much faster iteration, and direct TorchInductor integration. The shift feels real in […]

Ver mais

arXiv:2602.15071v1 Announce Type: new Abstract: “Intangible Victory” is an audiovisual installation in the form of the intangible being of the Victory of Samothrace that uses interactive digital media. Specifically, through this installation, we redefine the visual symbolism of the ancient sculpture, paying attention to time as a wear factor (entropy) and the special importance of the void as an absence of the sculptural form. Emptiness completes the intangible essence of the sculpture in the field of symbolism as […]

Ver mais

arXiv:2601.19368v1 Announce Type: cross Abstract: Generative diffusion models are extensively used in unsupervised and self-supervised machine learning with the aim to generate new samples from a probability distribution estimated with a set of known samples. They have demonstrated impressive results in replicating dense, real-world contents such as images, musical pieces, or human languages. This work investigates their application to the numerical simulation of incompressible fluid flows, with a view toward incorporating physical constraints such as incompressibility in the […]

Ver mais