Search Results for author:
Found 5 papers, 4 papers with code
Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary cases
Recent studies have demonstrated the capabilities of LLMs to automatically conduct prompt engineering by employing a meta-prompt that incorporates the outcomes of the last trials and proposes an improved prompt.
DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer
The ability to condition layout generation on a partial subset of component attributes is critical to real-world applications that involve user interaction.
Dynamic-Deep: Tune ECG Task Performance and Optimize Compression in IoT Architectures
Instead, we advocate a self-adapting lossy compression solution that enables configuring a desired performance level on the downstream tasks while maintaining an optimized CG that reduces Cloud costs.
Accurate Visual Localization for Automotive Applications
We propose a hybrid coarse-to-fine approach that leverages visual and GPS location cues.
Spatio-Temporal Action Graph Networks
Events defined by the interaction of objects in a scene are often of critical importance; yet important events may have insufficient labeled examples to train a conventional deep model to generalize to future object appearance.
