arXiv:2603.06666v1 Announce Type: new Abstract: Autoregressive (AR) image models have recently demonstrated remarkable generative capability, but their sequential nature results in significant inference latency. Existing training-free acceleration methods typically verify tokens independently, overlooking the strong co-occurrence patterns between adjacent visual tokens. This independence assumption often leads to contextual inconsistency and limits decoding efficiency. In this work, we introduce a novel training-free acceleration framework that performs phrase-level speculative verification, enabling the model to jointly validate multiple correlated tokens within […]

Ver mais

arXiv:2601.10744v1 Announce Type: new Abstract: An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only requires the agent to accurately accomplish given tasks but also to leverage long-term episodic memory to optimize decision-making. However, existing mainstream one-shot embodied tasks primarily focus on task completion results, neglecting the crucial process of exploration and memory utilization. To address this, we propose Long-term Memory Embodied Exploration (LMEE), […]

Ver mais

Second-order optimizers can significantly accelerate large-scale training, yet their naive federated variants are often unstable or even diverge on non-IID data. We show that a key culprit is emph{preconditioner drift}: client-side second-order training induces heterogeneous emph{curvature-defined geometries} (i.e., preconditioner coordinate systems), and server-side model averaging updates computed under incompatible metrics, corrupting the global descent direction. To address this geometric mismatch, we propose texttt{FedPAC}, a emph{preconditioner alignment and correction} framework for reliable federated second-order optimization. texttt{FedPAC} explicitly decouples parameter […]

Ver mais

arXiv:2601.03302v1 Announce Type: new Abstract: We present CageDroneRF (CDRF), a large-scale benchmark for Radio-Frequency (RF) drone detection and identification built from real-world captures and systematically generated synthetic variants. CDRF addresses the scarcity and limited diversity of existing RF datasets by coupling extensive raw recordings with a principled augmentation pipeline that (i) precisely controls Signal-to-Noise Ratio (SNR), (ii) injects interfering emitters, and (iii) applies frequency shifts with label-consistent bounding-box transformations for detection. This dataset spans a wide range of […]

Ver mais

Learning to coordinate many agents in partially observable and highly dynamic environments requires both informative representations and data-efficient training. To address this challenge, we present a novel model-based multi-agent reinforcement learning framework that unifies joint state-action representation learning with imaginative roll-outs. We design a world model trained with variational auto-encoders and augment the model using the state-action learned embedding (SALE). SALE is injected into both the imagination module that forecasts plausible future roll-outs and the joint agent network […]

Ver mais

arXiv:2602.22368v1 Announce Type: new Abstract: Code summarization is the task of generating natural language descriptions of source code, which is critical for software comprehension and maintenance. While large language models (LLMs) have achieved remarkable progress on this task, an open question remains: can human expertise in code understanding further guide and enhance these models? We propose EyeLayer, a lightweight attention-augmentation module that incorporates human eye-gaze patterns, as a proxy of human expertise, into LLM-based code summarization. EyeLayer models […]

Ver mais

One of the things I found off-putting about category theory when I was first exposed to it was its reliance on the notion of “collections” that are not sets. That seemed to place the entire theory on dubious foundations with paradoxes looming around every corner. It turns out you can mostly ignore such issues in application. You can, for example, talk about the forgetful functor that maps a group to the set of its elements, ignoring the group […]

Ver mais

Processing video is one of the heaviest tasks a web application can handle. If you are still running shell_exec(‘ffmpeg …’) inside a Controller, you are likely blocking your PHP-FPM threads, frustrating your users, and risking timeouts. In 2026, we don’t do that. We treat video processing as an asynchronous, distributed pipeline. With the release of Symfony 7.4, we have new tools that make this robust and native. We now have a dedicated #[Video] validation constraint, native support for shared directories, and the mature Messenger component to […]

Ver mais