Visual Autoregressive Priors for RAW-to-sRGB Image Signal Processing
本文使用视觉自回归模型处理RAW-to-sRGB图像信号，通过频率分解色彩损失优化，以恢复感知上忠实的颜色和细节。
0 citationsRead paper
Selected work
Representative Papers
PCBnet: A Dataset and Automatic Construction of SPICE Netlists from Schematic Images
为解决AI驱动的PCB设计自动化中缺乏大规模配对数据集的问题，通过构建包含300多个实际设计的PCBnet数据集，并开发自动化的原理图到网表转换流程。
0 citationsRead paper
StereoDiffuer: Diffusion-based Progressive Geometry Modeling with Saliency Attention Perception for Stereo Matching
本文提出StereoDiffuer框架，通过迭代扩散和显著性注意力感知模块解决立体匹配中几何细节保留问题，提高视差图质量。
0 citationsRead paper
Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant
Existing research lacks a dedicated benchmark for evaluating multi-agent frameworks in intelligent personal assistant scenarios. Method: We introduce Auto-SLURP, the first task-oriented benchmark specifically designed for this purpose. It re-annotates the SLURP dataset with executable task specifications, and integrates a reproducible execution environment with simulated external services to enable end-to-end evaluation of language understanding, task planning, tool invocation, and response generation. Contribution/Results: Auto-SLURP pioneers the transformation of traditional NLU datasets into a multi-agent system evaluation platform, overcoming the limitations of static intent classification. Empirical evaluation reveals that state-of-the-art multi-agent frameworks exhibit significant deficiencies in reliability and inter-agent coordination—particularly on long-horizon tasks. To foster community advancement, we open-source the benchmark data, implementation code, and standardized evaluation pipeline, establishing a foundational infrastructure for rigorous, comparable assessment of multi-agent assistants.
0 citationsRead paper
Recent publications
Latest Papers
Visual Autoregressive Priors for RAW-to-sRGB Image Signal Processing
本文使用视觉自回归模型处理RAW-to-sRGB图像信号，通过频率分解色彩损失优化，以恢复感知上忠实的颜色和细节。
0 citationsRead paper
PCBnet: A Dataset and Automatic Construction of SPICE Netlists from Schematic Images
为解决AI驱动的PCB设计自动化中缺乏大规模配对数据集的问题，通过构建包含300多个实际设计的PCBnet数据集，并开发自动化的原理图到网表转换流程。
0 citationsRead paper
StereoDiffuer: Diffusion-based Progressive Geometry Modeling with Saliency Attention Perception for Stereo Matching
本文提出StereoDiffuer框架，通过迭代扩散和显著性注意力感知模块解决立体匹配中几何细节保留问题，提高视差图质量。
0 citationsRead paper
Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant
Existing research lacks a dedicated benchmark for evaluating multi-agent frameworks in intelligent personal assistant scenarios. Method: We introduce Auto-SLURP, the first task-oriented benchmark specifically designed for this purpose. It re-annotates the SLURP dataset with executable task specifications, and integrates a reproducible execution environment with simulated external services to enable end-to-end evaluation of language understanding, task planning, tool invocation, and response generation. Contribution/Results: Auto-SLURP pioneers the transformation of traditional NLU datasets into a multi-agent system evaluation platform, overcoming the limitations of static intent classification. Empirical evaluation reveals that state-of-the-art multi-agent frameworks exhibit significant deficiencies in reliability and inter-agent coordination—particularly on long-horizon tasks. To foster community advancement, we open-source the benchmark data, implementation code, and standardized evaluation pipeline, establishing a foundational infrastructure for rigorous, comparable assessment of multi-agent assistants.
0 citationsRead paper