GitHub

ML-Decoder: Scalable and Versatile Classification Head

In this paper, we introduce ML-Decoder, a new attention-based classification head. ML-Decoder predicts the existence of class labels via queries, and enables better utilization of spatial data ...
GitHub

Return of the Encoder: Efficient Small Language Models

We note that our work focuses on architectural comparisons rather than competing with recent SLM developments (e.g., SmolLM, MobileLLM). Our analysis isolates the fundamental advantages of ...
IEEE

Inverse-Designed Low-Crosstalk CWDM (De)Multiplexer Assisted by Photonic Crystals

Abstract: Compact and integrated wavelength demultiplexers are key components of photonic integrated circuits for on-chip communications. The inverse design method has shown excellent performance in ...
IEEE

Inverse Design of a Wavelength (De)Multiplexer for 1.55- and 2-μm Wavebands by Using a Hybrid Analog-Digital Method

Abstract: Recently, the emerging 2-μm waveband has gained increasing interest due to its great potential for a wide scope of applications. The 2-μm waveband is considered a novel communication window ...