Junkai Chen

TCA-Net achieves superior low-light image enhancement by intelligently adapting attention mechanisms to prioritize high-confidence interactions, resulting in improved color fidelity and restoration accuracy.

Smaller models get a bigger speed boost from Speculative Decoding on software engineering tasks, challenging the assumption that larger models always benefit more from inference acceleration techniques.

Accurately simulate complex underwater robots, including soft and underactuated designs, without tedious manual tuning, by jointly optimizing structural and hydrodynamic parameters.