OpenAI is preparing a major structural shift: the company plans to reestablish itself as a for-profit business. A key step toward that goal came this week, as Microsoft agreed in principle to adjust the terms of their partnership. The article…
Man agreed to return more than 1,000 stolen DVDs to his former employer.
Authorities have named Tyler Robinson as a suspect in the murder of right-wing influencer Charlie Kirk, citing Discord messages as evidence of his alleged role.
Whether you’re shopping for a couple or updating your own registry, these are our favorite tried-and-tested gifts that’ll be enjoyed for years to come.
Ida Silfverskiöld on AI agents, RAG, evals, and what design choice ended up mattering more than expected The post Generalists Can Also Dig Deep appeared first on Towards Data Science.
Data is everywhere, but how do you draw insights from it? Often, structured data is stored in relational databases, meaning collections of related tables of data. For instance, a company might store customer purchases in one table, customer demographics in…
EU probe came after complaint by Slack in 2020.
Deepdub, an Israeli Voice AI startup, has introduced Lightning 2.5, a real-time foundational voice model designed to power scalable, production-grade voice applications. The new release delivers substantial improvements in performance and efficiency, positioning it for use in live interactive systems such as contact centers, AI agents, and real-time dubbing. Performance and Efficiency Lightning 2.5 achieves […] The post Deepdub Introduces Lightning 2.5: A Real-Time AI Voice Model With 2.8x Throughput Gains for Scalable AI Agents and Enterprise AI appeared first on MarkTechPost.
arXiv:2509.09210v1 Announce Type: new Abstract: Accurate motion prediction of surrounding agents is crucial for the safe planning of autonomous vehicles. Recent advancements have extended prediction techniques from individual agents to joint predictions of multiple interacting agents, with various strategies to address complex interactions within future motions of agents. However, these methods overlook the evolving nature of these interactions. To address this limitation, we propose a novel progressive multi-scale decoding strategy, termed ProgD, with the help of dynamic heterogeneous graph-based scenario modeling. In particular, to explicitly and comprehensively capture the evolving social interactions in future scenarios, given their inherent uncertainty, we design a progressive modeling of scenarios with dynamic heterogeneous graphs. With the unfolding of such dynamic heterogeneous graphs, a factorized architecture is designed to process the spatio-temporal dependencies within future scenarios and progressively eliminate uncertainty in future motions of multiple agents. Furthermore, a multi-scale decoding procedure is incorporated to improve on the future scenario modeling and consistent prediction of agents' future motion. The proposed ProgD achieves state-of-the-art performance on the INTERACTION multi-agent prediction benchmark, ranking $1^{st}$, and the Argoverse 2 multi-world forecasting benchmark.
arXiv:2508.04618v2 Announce Type: replace-cross Abstract: Recommender systems are indispensable for helping users navigate the immense item catalogs of modern online platforms. Recently, generative recommendation has emerged as a promising paradigm, unifying the conventional retrieve-and-rank pipeline into an end-to-end model capable of dynamic generation. However, existing generative methods are fundamentally constrained by their unsupervised tokenization, which generates semantic IDs suffering from two critical flaws: (1) they are semantically flat and uninterpretable, lacking a coherent hierarchy, and (2) they are prone to representation entanglement (i.e., ``ID collisions''), which harms recommendation accuracy and diversity. To overcome these limitations, we propose HiD-VAE, a novel framework that learns hierarchically disentangled item representations through two core innovations. First, HiD-VAE pioneers a hierarchically-supervised quantization process that aligns discrete codes with multi-level item tags, yielding more uniform and disentangled IDs. Crucially, the trained codebooks can predict hierarchical tags, providing a traceable and interpretable semantic path for each recommendation. Second, to combat representation entanglement, HiD-VAE incorporates a novel uniqueness loss that directly penalizes latent space overlap. This mechanism not only resolves the critical ID collision problem but also promotes recommendation diversity by ensuring a more comprehensive utilization of the item representation space. These high-quality, disentangled IDs provide a powerful foundation for downstream generative models. Extensive experiments on three public benchmarks validate HiD-VAE's superior performance against state-of-the-art methods. The code is available at https://anonymous.4open.science/r/HiD-VAE-84B2.
