A company that seeks to disrupt the way in which data from space is received and transmitted has found some key investors and customers. On Tuesday morning Northwood Space announced that it has closed a $100 million Series B round of funding to support a rapid ramp-up in the deployment of its phased-array radar system, known as Portal. The company also said it has received a $49.8 million contract from the US Space Force to augment the Satellite […]

Ver mais

arXiv:2605.04269v1 Announce Type: new Abstract: We provide a theoretical analysis of Adam under non-stationary stochastic objectives, separating two regimes: Euclidean tracking under adaptive strong monotonicity of the Adam-preconditioned mean-gradient operator, and high-probability projected stationarity guarantees under general $L$-smooth objectives. In the tracking regime, we derive finite-time expected and high-probability bounds that decompose sharply into four components: initialization, objective drift, a first-moment tracking error governed by $beta_1$, and a preconditioner perturbation governed by $beta_2$. We characterize the burn-in time […]

Ver mais

I’m behind on writing about Qwen 3.5, a truly remarkable family of open weight models released by Alibaba’s Qwen team over the past few weeks. I’m hoping that the 3.5 family doesn’t turn out to be Qwen’s swan song, seeing as that team has had some very high profile departures in the past 24 hours. It all started with this tweet from Junyang Lin (@JustinLin610): me stepping down. bye my beloved qwen. Junyang Lin was the lead researcher […]

Ver mais

arXiv:2603.26767v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic scene structure. We address this by proposing the first training-free framework specifically designed to tame DiTs for high-fidelity appearance transfer. Our core is a synergistic system that disentangles structure and appearance. We leverage high-fidelity inversion to establish a rich content prior for the […]

Ver mais

arXiv:2511.18737v2 Announce Type: replace-cross Abstract: We consider the problem of joint estimation of the parameters of $m$ linear dynamical systems, given access to single realizations of their respective trajectories, each of length $T$. The linear systems are assumed to reside on the nodes of an undirected and connected graph $G = ([m], mathcal{E})$, and the system matrices are assumed to either vary smoothly or exhibit small number of “jumps” across the edges. We consider a total variation penalized […]

Ver mais

arXiv:2602.02546v1 Announce Type: new Abstract: Large language models (LLMs) deliver strong performance, but their high compute and memory costs make deployment difficult in resource-constrained scenarios. Weight-only post-training quantization (PTQ) is appealing, as it reduces memory usage and enables practical speedup without low-bit operators or specialized hardware. However, accuracy often degrades significantly in weight-only PTQ at sub-4-bit precision, and our analysis identifies two main causes: (1) down-projection matrices are a well-known quantization bottleneck, but maintaining their fidelity often requires […]

Ver mais

arXiv:2604.13206v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly integrated into agentic workflows, their unpredictability stemming from numerical instability has emerged as a critical reliability issue. While recent studies have demonstrated the significant downstream effects of these instabilities, the root causes and underlying mechanisms remain poorly understood. In this paper, we present a rigorous analysis of how unpredictability is rooted in the finite numerical precision of floating-point representations, tracking how rounding errors propagate, amplify, or […]

Ver mais

arXiv:2603.24821v1 Announce Type: new Abstract: State-of-the-art crowd counting and localization are primarily modeled using two paradigms: density maps and point regression. Given the field’s security ramifications, there is active interest in model robustness against adversarial attacks. Recent studies have demonstrated transferability across density-map-based approaches via adversarial patches, but cross-paradigm attacks (i.e., across both density map-based models and point regression-based models) remain unexplored. We introduce a novel adversarial framework that compromises both density map and point regression architectural paradigms […]

Ver mais

Reinforcement Learning (RL) has been shown to substantially improve the reasoning capability of small and large language models (LLMs), but existing approaches typically rely on verifiable rewards, hence ground truth labels. We propose an RL framework that uses rewards from an LLM that acts as a judge evaluating model outputs over large amounts of unlabeled data, enabling label-free knowledge distillation and replacing the need of ground truth supervision. Notably, the judge operates with a single-token output, making reward […]

Ver mais