Searcharxiv⌕ Search

arXiv subjects

Yizheng Li

Publications and source records attributed to Yizheng Li.

7 recordsLinked to original sources

Well-Log Reconstruction with Pre-trained Geological Knowledge: A Knowledge-Conditioned Large-Language-Model Generative Agent

Missing well-log intervals make subsurface reconstruction ill-posed. Existing numerical regression models lack geological prior knowledge to constrain ambiguous inverse mappings. We propose GeoLog-Agent, a knowledge-conditioned generative agent using pre-trained large language models (LLMs) as a source of geological priors. A universal Geo-Harness translates LLM stratigraphic reasoning into formation-anchored petrophysical trajectories, feature-wise linear modulation, and conditional adversarial constraints. On the Norwegian North Sea benchmark, GeoLog-Agent achieves a mean $R^2$ of 0.9307 and a peak $R^2$ of 0.9713. It exceeds the nine-baseline average $R^2$ of 0.8387 by 0.0920, with a 30.97% average RMSE reduction, and exceeds the strongest baseline by 0.0274--0.0498 in $R^2$, with 16.25%--24.05% lower RMSE. Ablations confirm the effectiveness and synergy of geological prior reasoning, multi-scale dilated generation, and conditional adversarial modules. Transferring the coupling mechanism to six conventional deep learning models improves their $R^2$ by 0.0162--0.0789 with cross-well stability. These results demonstrate how foundation-model domain reasoning can constrain deep generative reconstruction of missing petrophysical measurements.

cs.LG↗

Robust Well-Log Reconstruction Across Point Gaps and Whole Wells via Boundary-Gated Soft-Thresholding Kalman Fusion

Missing wireline logs hinder subsurface characterization. Deep reconstruction networks suffer from gap-boundary steps and cross-basin shifts, while interpolation and Gaussian smoothers struggle with long intervals and outliers. We propose boundary-gated soft-thresholding Kalman fusion (ST-KF), unifying multiresolution wavelet shrinkage, distance-gated residual prior learning, and closed-form robust Kalman smoothing with learning--inference decoupling. Across two public benchmarks totaling 263 wells in the Norwegian North Sea and New Zealand's Taranaki Basin, ST-KF ranks first over 0.15--100-m anchored gaps with 0.09% parameter overhead. Against the strongest of nine baselines, pooled RMSE falls by 5.0%--8.3% for bulk density and 6.4%--15.6% for compressional slowness; against the four strongest baselines, reductions are 0.7%--4.1% for neutron porosity and 1.3%--2.9% for photoelectric factor. Ablations and sensitivity analyses confirm operator synergy and stable performance: removing state-space fusion increases short-gap errors by up to 58.8%, while zero-shot transfer cuts anchored errors by 14%--68%. The results show that local borehole continuity transfers across basins whereas cross-property mappings shift with regional geology, supporting measurement-guided log reconstruction.

cs.LG↗

From Sliding Windows to Self-evolving Lifelong Memory: A Dual-perspective Survey of Memory Paradigms for Long-Horizon Robotics VLA Models

Long-horizon robotic tasks expose a fundamental limitation of current Vision-Language-Action (VLA) models because their restricted temporal context pre-vents effective accumulation and reuse of past experiences. As a result, memory has become a fundamental component for enabling embodied agents to perform long-horizon reasoning and adaptive decision-making. This survey presents a systematic taxonomy of VLA memory mechanisms based on memory scope and persistence, categorizing existing approaches into five representative paradigms and one emerging frontier. Based on this taxonomy, we compare representative VLA memory systems in terms of memory characteristics, architectural com-plexity, and open-source maturity, revealing a clear trade-off in which increasing architectural complexity is generally accompanied by decreasing open-source ma-turity. Finally, we discuss the key challenges in building full-lifecycle memory systems, including efficient memory management and lifelong knowledge evolu-tion. Overall, this survey provides a unified perspective on memory architectures for VLA agents and offers insights into the development of lifelong embodied in-telligence.

cs.RO↗

Cohomology and Deformation theory of crossed homomorphisms on Leibniz algebras

In this paper, we construct a differential graded Lie algebra whose Maurer-Cartan elements are given by crossed homomorphisms on Leibniz algebras. This allows us to define cohomology for a crossed homomorphism. Finally, we study linear deformations, formal deformations and extendibility of finite order deformations of a crossed homomorphism in terms of the cohomology theory.

math.RA↗

$n$-dervations of Lie color algebras

The aim of this article is to discuss the $n$-derivation algebras of Lie color algebras. It is proved that, if the base ring contains $\frac{1}{n-1}$, $L$ is a perfect Lie color algebra with zero center, then every triple derivation of $L$ is a derivation, and every $n$-derivation of the derivation algebra $nDer(L))$ is an inner derivation.

math.RA↗

Yetter-Drinfeld modules for weak Hom-Hopf algebras

The aim of this paper is to define and study Yetter-Drinfeld modules over weak Hom-Hopf algebras. We show that the category ${}_H{\cal WYD}^H$ of Yetter-Drinfeld modules with bijective structure maps over weak Hom-Hopf algebras is a rigid category and a braided monoidal category, and obtain a new solution of quantum Hom-Yang-Baxter equation. It turns out that, If $H$ is quasitriangular (respectively, coquasitriangular)weak Hom-Hopf algebras, the category of modules (respectively, comodules) with bijective structure maps over $H$ is a braided monoidal subcategory of the category ${}_H{\cal WYD}^H$ of Yetter-Drinfeld modules over weak Hom-Hopf algebras.

math.RA↗