Assume addition H3andset k =O(1/ p k). Foranyn 1,

Multimodal AI models are increasingly used in fields like healthcare, finance, and autonomous driving, where information is drawn from multiple sources or modalities such as images, texts, audios, videos. However, effectively managing uncertainty - arising from noise, insufficient evidence, or conflicts between modalities - is crucial for reliable decision-making. Current uncertainty-aware ML methods leveraging, for example, evidence averaging, or evidence accumulation underestimate uncertainties in high-conflict scenarios. Moreover, the state-of-the-art evidence averaging strategy struggles with non-associativity and fails to scale to multiple modalities. To address these challenges, we propose a novel multimodal learning method with order-invariant evidence fusion and introduce a conflict-based discounting mechanism that reallocates uncertain mass when unreliable modalities are detected. We provide both theoretical analysis and experimental validation, demonstrating that unlike the previous work, the proposed approach effectively distinguishes between conflicting and non-conflicting samples based on the provided uncertainty estimates, and outperforms the previous models in uncertainty-based conflict detection.

The second generation of Robotic Operating System, ROS 2, has gained much attention for its potential to be used for safety-critical robotic applications. The need to provide a solid foundation for timing correctness and scheduling mechanisms is therefore growing rapidly. Although there are some pioneering studies conducted on formally analyzing the response time of processing chains in ROS 2, the focus has been limited to single-threaded executors, and multi-threaded executors, despite their advantages, have not been studied well. To fill this knowledge gap, in this paper, we propose a comprehensive response-time analysis framework for chains running on ROS 2 multi-threaded executors. We first analyze the timing behavior of the default scheduling scheme in ROS 2 multi-threaded executors, and then present priority-driven scheduling enhancements to address the limitations of the default scheme. Our framework can analyze chains with both arbitrary and constrained deadlines and also the effect of mutually-exclusive callback groups. Evaluation is conducted by a case study on NVIDIA Jetson AGX Xavier and schedulability experiments using randomly-generated chains. The results demonstrate that our analysis framework can safely upper-bound response times under various conditions and the priority-driven scheduling enhancements not only reduce the response time of critical chains but also improve analytical bounds.

Let h be a heuristic function selected for expansions when GBFS with the FF heuristic that estimates the distance to a goal from a node n. GBFS (Hoffmann and Nebel 2001) solves a planning problem. The selects the best node n with the smallest h(n) in the open list horizontal axis indicates each expansion of the best node that maintains nodes that have been generated but have not n in the open list and the vertical axis represents n's corresponding been expanded yet. It then expands n to generate n's successors, heuristic value for that expansion. Circles, the and saves these successors in the open list, unless triangle, and diamond represent expanding nodes that are they have been previously added to the open list.

Heuristic functions play an important role in drastically improving performance of satisficing planners based on greedy best-first search (GBFS). While automatic generation of heuristic functions (e.g., (Hoffmann and Nebel 2001; Helmert 2006)) enables state-of-the-art satisficing planners to solve very complicated planning problems including benchmarks in the International Planning Competitions, accurate evaluations of nodes still remain as a challenging task. Although GBFS is fundamental and powerful in planning, it has an essential drawback when heuristic functions return inaccurate estimates. Assume that a heuristic function underestimates the difficulties of unpromising nodes. Then, since GBFS must expand nodes with small heuristic values first, it spends most of time in searching only unpromising areas and delays moving to the promising part. Previous work tackles this issue by adding a diversity to search, which is an ability in simultaneously exploring different parts of the search space to bypass large errors in heuristic functions. Several algorithms combined with diversity (e.g., K-best-first search (KBFS) in (Felner, Kraus, and Korf 2003)) are empirically shown to be superior to naive best-first search algorithms. However, they still have limited diversity, since they do not immediately expand nodes mistakenly evaluated as very unpromising ones. This paper presents a new technique called diverse best-first search (DBFS) , which incorporates a diversity into search in a different way than previous search-based approaches. We show empirical results clearly showing that DBFS is effective in satisficing planning.