Selected work

Representative Papers

MoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image Pairs

Oct 05, 2026

This study addresses the challenge of 3D reconstruction from sparse lunar images characterized by weak textures and low overlap. We propose the first feed-forward 3D Gaussian Splatting framework tailored for lunar scenes. By predicting Gaussian primitives and rendering novel views through a single forward pass from only two input views, our method eliminates the need for per-scene optimization. Furthermore, it integrates depth features from vision foundation models with semantic priors and introduces an entropy-guided heuristic resampling strategy to effectively enhance geometric consistency under sparse observations. Experimental results demonstrate that the proposed approach achieves state-of-the-art performance on both the LuSNAR dataset and Chang'e mission data, yielding a 4.9 dB improvement in PSNR, a 40% reduction in LPIPS, and sub-second inference speed.

0 citationsRead paper

Self-Spec Verifiable Code Generation

Sep 30, 2026

This study addresses the limitations of existing benchmarks, which lack evaluation of end-to-end self-generated specification–code verification linkages and fail to cover multilingual real-world scenarios. To bridge this gap, we propose VeriCodeBench, a comprehensive benchmark, alongside CodeNova, a novel framework that pioneers an end-to-end self-specifying verifiable code generation paradigm. In this approach, large language models autonomously generate constraint-guided formal specifications and corresponding code, while verifier feedback drives targeted repair, establishing a full closed-loop pipeline across C, Java, Rust, and Python. Experimental results demonstrate that our method yields significant improvements across all evaluated metrics. Notably, Claude Sonnet 5 achieves state-of-the-art performance under the self-specification protocol. Furthermore, our analysis reveals that specification generation remains the primary bottleneck in current verifiable code synthesis pipelines.

0 citationsRead paper

DualManip: Agentic Dynamic Manipulation via Dual-Path Semantic Reasoning and Geometric Adaptation

Sep 25, 2026

This study addresses the high inference latency and inadequate responsiveness of vision-language models in dynamic robotic manipulation by proposing a dual-path framework that decouples low-frequency semantic reasoning from high-frequency geometric adaptation. Methodologically, an information interaction module bridges the two pathways to enable online grasp reconstruction and semantic replanning upon failure, while integrating a shape-adaptive network, constraint solving, and real-time RGB-D observations to achieve continuous geometric correspondence updates. Experimental results demonstrate that the proposed approach exhibits superior robustness across six task categories and accelerates geometric adaptation by approximately 46 times compared to conventional verification-based methods.

0 citationsRead paper

PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation

Sep 15, 2026

本文提出PriorPose，通过参考引导的对应框架联合解决类别级物体姿态估计中的规范化和对齐问题，提高在形状变化和域迁移下的鲁棒性。

0 citationsRead paper

Generics-Aware Fuzz Target Generation for Rust Libraries via Structured API Analysis

Aug 09, 2026

Existing fuzzing tools struggle to generate compilable API call sequences that satisfy Rust’s ownership, generic, and trait constraints, resulting in low coverage. This work proposes a novel approach that constructs a generic- and trait-aware API dependency graph through structured parsing of Rust documentation, then combines topological-guided traversal with large language model–based code synthesis, iteratively refining test cases under compiler feedback. To the best of our knowledge, this is the first method to systematically model generic and trait constraints for fuzzing. Evaluated on 13 real-world crates, it achieves an average API coverage of 80.75% and a compilation success rate of 96.19%, outperforming RULF, RPG, and deepSURF by factors of 4.76×, 2.43×, and 1.41× in coverage, respectively.

0 citationsRead paper

Recent publications

Latest Papers

MoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image Pairs

Oct 05, 2026

This study addresses the challenge of 3D reconstruction from sparse lunar images characterized by weak textures and low overlap. We propose the first feed-forward 3D Gaussian Splatting framework tailored for lunar scenes. By predicting Gaussian primitives and rendering novel views through a single forward pass from only two input views, our method eliminates the need for per-scene optimization. Furthermore, it integrates depth features from vision foundation models with semantic priors and introduces an entropy-guided heuristic resampling strategy to effectively enhance geometric consistency under sparse observations. Experimental results demonstrate that the proposed approach achieves state-of-the-art performance on both the LuSNAR dataset and Chang'e mission data, yielding a 4.9 dB improvement in PSNR, a 40% reduction in LPIPS, and sub-second inference speed.

0 citationsRead paper

Self-Spec Verifiable Code Generation

Sep 30, 2026

This study addresses the limitations of existing benchmarks, which lack evaluation of end-to-end self-generated specification–code verification linkages and fail to cover multilingual real-world scenarios. To bridge this gap, we propose VeriCodeBench, a comprehensive benchmark, alongside CodeNova, a novel framework that pioneers an end-to-end self-specifying verifiable code generation paradigm. In this approach, large language models autonomously generate constraint-guided formal specifications and corresponding code, while verifier feedback drives targeted repair, establishing a full closed-loop pipeline across C, Java, Rust, and Python. Experimental results demonstrate that our method yields significant improvements across all evaluated metrics. Notably, Claude Sonnet 5 achieves state-of-the-art performance under the self-specification protocol. Furthermore, our analysis reveals that specification generation remains the primary bottleneck in current verifiable code synthesis pipelines.

0 citationsRead paper

DualManip: Agentic Dynamic Manipulation via Dual-Path Semantic Reasoning and Geometric Adaptation

Sep 25, 2026

This study addresses the high inference latency and inadequate responsiveness of vision-language models in dynamic robotic manipulation by proposing a dual-path framework that decouples low-frequency semantic reasoning from high-frequency geometric adaptation. Methodologically, an information interaction module bridges the two pathways to enable online grasp reconstruction and semantic replanning upon failure, while integrating a shape-adaptive network, constraint solving, and real-time RGB-D observations to achieve continuous geometric correspondence updates. Experimental results demonstrate that the proposed approach exhibits superior robustness across six task categories and accelerates geometric adaptation by approximately 46 times compared to conventional verification-based methods.

0 citationsRead paper

PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation

Sep 15, 2026

本文提出PriorPose，通过参考引导的对应框架联合解决类别级物体姿态估计中的规范化和对齐问题，提高在形状变化和域迁移下的鲁棒性。

0 citationsRead paper

Generics-Aware Fuzz Target Generation for Rust Libraries via Structured API Analysis

Aug 09, 2026

Existing fuzzing tools struggle to generate compilable API call sequences that satisfy Rust’s ownership, generic, and trait constraints, resulting in low coverage. This work proposes a novel approach that constructs a generic- and trait-aware API dependency graph through structured parsing of Rust documentation, then combines topological-guided traversal with large language model–based code synthesis, iteratively refining test cases under compiler feedback. To the best of our knowledge, this is the first method to systematically model generic and trait constraints for fuzzing. Evaluated on 13 real-world crates, it achieves an average API coverage of 80.75% and a compilation success rate of 96.19%, outperforming RULF, RPG, and deepSURF by factors of 4.76×, 2.43×, and 1.41× in coverage, respectively.

0 citationsRead paper