Yu-Yu Luo

Even state-of-the-art MLLMs struggle to grasp the nuanced data interpretation and narrative coherence required for data videos, with significant performance gaps in causal reasoning and narrative structure.

DataMagic achieves over 95% success rate and an 83% quality improvement in data video generation by declaratively orchestrating multi-agent scene creation, surpassing even state-of-the-art LLMs.

AnnoIndex achieves a remarkable F1 score of 0.87 by transforming unstructured text into a structured format, enabling precise analytical queries that traditional methods struggle with.

DataSpace reveals that even the best multimodal models struggle with data agent accuracy, achieving only 66.34% in complex heterogeneous environments.

LLM performance in vibration energy harvester design is stage-dependent, with no single model consistently outperforming others across the entire workflow.

Automated strategy optimization using LLMs can boost Sharpe ratios by over 199%, revolutionizing quantitative trading practices.

Interaction inference from screenshots remains a critical challenge, with top models lagging far behind in functional execution despite high visual fidelity.

CSTrader turns chaotic community-driven discussions into profitable trading strategies, achieving returns that defy traditional market predictions.

SQLConductor achieves a remarkable 73.2% execution accuracy by dynamically adapting SQL orchestration based on real-time feedback and intermediate results.

Transforming raw data into interactive narrative videos, DataMagic bridges the gap between data analysis and storytelling, enhancing how insights are communicated.

TUNEAHEAD can predict fine-tuning performance with remarkable accuracy, potentially saving researchers from costly and ineffective training runs.

As AI agents scale and interact, the Foundation Protocol offers a coordination layer that prioritizes accountability and governance, ensuring that the future of human-AI collaboration remains open and governable.

NL2SQL evaluation has a new champion: ROSE, an intent-centered metric that aligns 24% better with human judgment than existing metrics.

Forget slow, bloated LLMs – this work shows you can get GPT-4o quality on long-document QA with a 3B model and a clever structure-first distillation approach.

Forget vector embeddings: DocSage uses SQL-powered indexing and relational tables to achieve 27% higher accuracy on multi-document question answering.

Stop struggling with SQL dialects: Dial offers a knowledge-grounded approach that boosts NL2SQL accuracy by 10% and feature coverage by 15% across diverse database systems.

LLMs struggle to generate valid and executable ISO-GQL queries, achieving only 4% execution accuracy in zero-shot settings, highlighting a significant gap in their ability to interact with graph databases.