Selected work

Representative Papers

Active Mapping of Underwater Litter Using Camera-Sonar Fusion

Sep 30, 2026

This study addresses the limitations of single-sensor perception and inefficient path planning in low-visibility underwater environments by proposing an active mapping framework that fuses camera and sonar data. The method constructs a shared Bayesian occupancy map integrated with range-dependent detection probability modeling, and designs a dual-term utility scoring mechanism based on voxel entropy to balance exploration and exploitation, thereby enabling dynamic real-time optimization of observation viewpoints. Simulation results demonstrate that this fusion strategy significantly outperforms unimodal sensing approaches and achieves more efficient target localization compared to traditional lawnmower paths. This work provides a novel paradigm for autonomous exploration in complex underwater environments.

0 citationsRead paper

Finite-Context Semantics in Finitely Supported Structures

Sep 25, 2026

This study addresses the semantic incompleteness of systems with names and data, arising from the non-complete lattice structure of finitely supported predicate spaces, which impedes fixed-point existence guarantees. To overcome this, the work develops a theory of finitely supported structures over arbitrary permutation groups, introducing support-shifting bounds and uniform finiteness. By integrating group theory, invariant logic, and ultrahomogeneous atomic structures with abstract interpretation and resource rewriting techniques, it establishes a rigorous formalization framework. The authors prove that monotone transformers admit least and greatest fixed points under specific conditions, revealing a novel mechanism whereby Boolean predicates achieve finite iterative convergence even with infinitely many orbits, thereby decoupling semantic existence, convergence, and computation. These results are successfully applied to automata theory and operational semantics, validating the effectiveness of the proposed approach.

0 citationsRead paper

Finite Dependence and Invariance Hierarchies for Finitely Supported Structures

Sep 14, 2026

研究通过有限支持集X^S和不变性层次B^{(n)}_{G,S}探讨了有限支持结构的依赖性和不变性问题，提出并验证了几种名义原则的有效性。

0 citationsRead paper

MBO Scheme for Local Chan--Vese Segmentation

Aug 01, 2026

This work addresses the limited robustness of the local Chan–Vese model to intensity inhomogeneity and the computational inefficiency of conventional finite difference schemes by introducing, for the first time, the Merriman–Bence–Osher (MBO) scheme into this framework. The proposed method formulates an efficient variational level set approach grounded in local image statistics, significantly accelerating computation while naturally accommodating two-phase, multi-phase, and color image segmentation. Extensive experiments on diverse datasets—including medical and microscopic images—demonstrate that the algorithm achieves superior segmentation accuracy and speed compared to traditional finite difference methods, all while maintaining high robustness to intensity variations.

0 citationsRead paper

The GEST-Engine: From Event Graphs to Synthetic Video. A Full Technical Report

Jul 13, 2026

This work proposes an end-to-end framework for generating semantically coherent, spatiotemporally consistent, and multi-agent coordinated synthetic videos from natural language descriptions. The core innovation lies in the integration of a structured, executable event graph (GEST) with an explicit world model, orchestrated by a large language model (LLM) as a director agent, a procedural state backend, and a temporal constraint solver based on Allen’s interval algebra and the Floyd–Warshall algorithm. This system deterministically executes multi-agent interaction scripts within a commercial game engine, producing in a single simulation synchronized outputs including RGB video, depth maps, instance segmentation masks, skeletal poses, bounding boxes, spatial relation graphs, event-to-frame alignments, and corresponding linguistic descriptions. The approach enables zero-marginal-cost generation of densely annotated multimodal data, offering high-quality training and evaluation resources for video understanding and generation tasks.

0 citationsRead paper

Recent publications

Latest Papers

Active Mapping of Underwater Litter Using Camera-Sonar Fusion

Sep 30, 2026

This study addresses the limitations of single-sensor perception and inefficient path planning in low-visibility underwater environments by proposing an active mapping framework that fuses camera and sonar data. The method constructs a shared Bayesian occupancy map integrated with range-dependent detection probability modeling, and designs a dual-term utility scoring mechanism based on voxel entropy to balance exploration and exploitation, thereby enabling dynamic real-time optimization of observation viewpoints. Simulation results demonstrate that this fusion strategy significantly outperforms unimodal sensing approaches and achieves more efficient target localization compared to traditional lawnmower paths. This work provides a novel paradigm for autonomous exploration in complex underwater environments.

0 citationsRead paper

Finite-Context Semantics in Finitely Supported Structures

Sep 25, 2026

This study addresses the semantic incompleteness of systems with names and data, arising from the non-complete lattice structure of finitely supported predicate spaces, which impedes fixed-point existence guarantees. To overcome this, the work develops a theory of finitely supported structures over arbitrary permutation groups, introducing support-shifting bounds and uniform finiteness. By integrating group theory, invariant logic, and ultrahomogeneous atomic structures with abstract interpretation and resource rewriting techniques, it establishes a rigorous formalization framework. The authors prove that monotone transformers admit least and greatest fixed points under specific conditions, revealing a novel mechanism whereby Boolean predicates achieve finite iterative convergence even with infinitely many orbits, thereby decoupling semantic existence, convergence, and computation. These results are successfully applied to automata theory and operational semantics, validating the effectiveness of the proposed approach.

0 citationsRead paper

Finite Dependence and Invariance Hierarchies for Finitely Supported Structures

Sep 14, 2026

研究通过有限支持集X^S和不变性层次B^{(n)}_{G,S}探讨了有限支持结构的依赖性和不变性问题，提出并验证了几种名义原则的有效性。

0 citationsRead paper

MBO Scheme for Local Chan--Vese Segmentation

Aug 01, 2026

This work addresses the limited robustness of the local Chan–Vese model to intensity inhomogeneity and the computational inefficiency of conventional finite difference schemes by introducing, for the first time, the Merriman–Bence–Osher (MBO) scheme into this framework. The proposed method formulates an efficient variational level set approach grounded in local image statistics, significantly accelerating computation while naturally accommodating two-phase, multi-phase, and color image segmentation. Extensive experiments on diverse datasets—including medical and microscopic images—demonstrate that the algorithm achieves superior segmentation accuracy and speed compared to traditional finite difference methods, all while maintaining high robustness to intensity variations.

0 citationsRead paper

The GEST-Engine: From Event Graphs to Synthetic Video. A Full Technical Report

Jul 13, 2026

This work proposes an end-to-end framework for generating semantically coherent, spatiotemporally consistent, and multi-agent coordinated synthetic videos from natural language descriptions. The core innovation lies in the integration of a structured, executable event graph (GEST) with an explicit world model, orchestrated by a large language model (LLM) as a director agent, a procedural state backend, and a temporal constraint solver based on Allen’s interval algebra and the Floyd–Warshall algorithm. This system deterministically executes multi-agent interaction scripts within a commercial game engine, producing in a single simulation synchronized outputs including RGB video, depth maps, instance segmentation masks, skeletal poses, bounding boxes, spatial relation graphs, event-to-frame alignments, and corresponding linguistic descriptions. The approach enables zero-marginal-cost generation of densely annotated multimodal data, offering high-quality training and evaluation resources for video understanding and generation tasks.

0 citationsRead paper