Search papers, labs, and topics across Lattice.
Beijing Institute of Technology
5
0
10
OpenRTAG reveals that traditional GNNs struggle significantly more than LLM-GNNs under realistic data quality degradation, highlighting critical vulnerabilities in graph learning models.
Sequence models can significantly outperform traditional approaches in PV power forecasting, especially under high levels of weather prediction uncertainty.
Current AI agents struggle with long-horizon professional tasks, achieving only 30% success in complex GUI workflows, revealing critical gaps in their capabilities.
Video codecs can slash LLM perplexity by over 1.5x while boosting task accuracy by 21%, revolutionizing model compression strategies.
Achieve zero-shot remote sensing image segmentation by cleverly fusing MLLM reasoning with geometric refinement, sidestepping the need for costly training data.
