SkillNet: Create, Evaluate, and Connect AI Skills
为解决AI技能缺乏系统积累和转移的问题，提出SkillNet，一个创建、评估和组织AI技能的开放基础设施。
Selected work
Representative Papers
A multimodal large language model for evidence-based autism spectrum disorder screening
为解决自闭症谱系障碍早期筛查瓶颈，提出ASDchat模型，采用视频、音频和对话作为输入，基于双分支架构进行筛查并生成行为证据。
0 citationsRead paper
CF-YOLO: Context-Aware Feature Refinement for Camouflaged Industrial Micro-Defect Detection
本文提出CF-YOLO框架，通过上下文感知聚合模块和特征加性精炼模块解决工业微缺陷检测中的背景伪装问题，提高检测精度。
0 citationsRead paper
Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning
研究通过提出知识边界感知路由器，选择性地在科学推理中使用条件记忆，以增强模型性能并避免负面影响。
0 citationsRead paper
VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation
This study addresses the absence of verifiable reasoning benchmarks and deterministic evaluation methods for Chinese abusive speech moderation by constructing a specialized evaluation benchmark. It innovatively proposes field-anchored chain-of-thought reasoning with structured output protocols and designs deterministic metrics that eliminate reliance on LLM judges, thereby enabling auditable verification of reasoning processes. The research reveals that strong label performance often masks deficiencies in record completeness. Furthermore, it provides a reproducible evaluation framework supporting zero-shot prompting and taxonomy-guided classification. Collectively, this work fills a critical gap in structured reasoning verification within the domain of content moderation, offering robust methodologies for ensuring both accuracy and transparency in automated detection systems.
0 citationsRead paper
Recent publications
Latest Papers
A multimodal large language model for evidence-based autism spectrum disorder screening
为解决自闭症谱系障碍早期筛查瓶颈，提出ASDchat模型，采用视频、音频和对话作为输入，基于双分支架构进行筛查并生成行为证据。
0 citationsRead paper
CF-YOLO: Context-Aware Feature Refinement for Camouflaged Industrial Micro-Defect Detection
本文提出CF-YOLO框架，通过上下文感知聚合模块和特征加性精炼模块解决工业微缺陷检测中的背景伪装问题，提高检测精度。
0 citationsRead paper
Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning
研究通过提出知识边界感知路由器，选择性地在科学推理中使用条件记忆，以增强模型性能并避免负面影响。
0 citationsRead paper
VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation
This study addresses the absence of verifiable reasoning benchmarks and deterministic evaluation methods for Chinese abusive speech moderation by constructing a specialized evaluation benchmark. It innovatively proposes field-anchored chain-of-thought reasoning with structured output protocols and designs deterministic metrics that eliminate reliance on LLM judges, thereby enabling auditable verification of reasoning processes. The research reveals that strong label performance often masks deficiencies in record completeness. Furthermore, it provides a reproducible evaluation framework supporting zero-shot prompting and taxonomy-guided classification. Collectively, this work fills a critical gap in structured reasoning verification within the domain of content moderation, offering robust methodologies for ensuring both accuracy and transparency in automated detection systems.
0 citationsRead paper
Acoustic-driven millimetric helical robot: ultrasonic synergistic manipulation in confined fluidic environment
Millimeter-scale robots often suffer from poor controllability in confined biological fluids due to low efficiency of acoustic actuation. This work proposes a multi-acoustic-field cooperative driving strategy that, for the first time, integrates acoustic radiation force and acoustic streaming effects at the millimeter scale, overcoming the efficiency limitations of conventional acoustic actuation in biologically constrained environments. Through multiphysics simulations and experimental validation, the approach enables multi-degree-of-freedom controllable motion on horizontal, inclined, and vertical planes. Unidirectional and reciprocating navigation have been successfully demonstrated within ex vivo porcine venous vessels, significantly enhancing the robot’s maneuverability and control precision in biologically relevant confined settings.
0 citationsRead paper