H2OFlow: Grounding Human-Object Affordances with 3D Generative Models and Dense Diffused Flows

Backdoor attacks represent a significant risk to deep learning, particularly in critical 3D applications like autonomous driving and robotics. Current methods primarily focus on static one-to-one attacks, leaving the more versatile one-to-N backdoor threat largely unaddressed. The introduction of STONE (Spherical Trigger One-to-N Backdoor Enabling) marks a pivotal advancement, offering a configurable spherical trigger that can manipulate multiple output labels while maintaining high accuracy in clean data.

Wave-Former is a new method for high-accuracy 3D shape reconstruction of completely occluded everyday objects. Utilizing millimeter-wave (mmWave) wireless signals, it can penetrate common obstructions and reflect off hidden items. Unlike previous methods that faced limitations in coverage and noise, Wave-Former employs a physics-aware shape completion model to infer full 3D geometry. Its innovative three-stage pipeline connects raw wireless signals with advancements in vision-based shape completion, enhancing applications in robotics, augmented reality, and logistics.

The article discusses a novel approach to optimizing federated learning through a method called FedEntOpt. This technique addresses privacy concerns associated with centralized datasets by allowing multiple clients to collaboratively train a global deep learning model without exposing their data. FedEntOpt enhances model performance by selecting clients based on the entropy of the aggregated label distribution, effectively mitigating issues related to label skew. Experiments demonstrate that this method improves classification accuracy by up to 6% compared to existing algorithms.

Graph learning is essential for analyzing complex relationships in graph data, with applications in social, citation, and e-commerce networks. Despite the success of foundation models in computer vision (CV) and natural language processing (NLP), existing graph learning methods often lack generalization across domains. Cross-domain graph learning (CDGL) has emerged as a promising approach, aiming to create true graph foundation models. This survey reviews current CDGL research and proposes a taxonomy based on transferable knowledge types: structure-oriented, feature-oriented, and mixture-orien…

The integration of Large Language Models (LLMs) with 3D vision is revolutionizing robotic perception and autonomy. This approach enhances robotic sensing technologies, allowing machines to understand and interact with complex environments using natural language and spatial awareness. The review discusses the foundational principles of LLMs and 3D data, examines critical 3D sensing technologies, and highlights advancements in scene understanding, text-to-3D generation, and embodied agents, while addressing the challenges faced in this evolving field.

The X-VMamba model introduces a controllability-based interpretability framework for State Space Models (SSMs), particularly the Mamba architecture. This framework aims to clarify how Vision SSMs process spatial information, which has been a challenge due to the absence of transparent mechanisms. The proposed methods include a Jacobian-based approach for any SSM architecture and a Gramian-based method for diagonal SSMs, both designed to enhance understanding of internal state dynamics while maintaining computational efficiency.

The article discusses the growing interest in world models, particularly in the context of advancements in multimodal large language models like GPT-4 and video generation models such as Sora. It provides a comprehensive review of the literature on world models, which serve to either understand the current state of the world or predict future dynamics. The review categorizes world models based on their functions: constructing internal representations and predicting future states, with applications in generative games, autonomous driving, robotics, and social simulacra.

Disney star has introduced AI avatars representing deceased individuals, marking a significant development in the intersection of entertainment and artificial intelligence. This debut showcases the potential of AI technology to create lifelike representations of those who have passed away, raising questions about ethics and the future of digital personas. The event took place on November 17, 2025, and is expected to attract attention from both fans and industry experts alike.