Related papers: Integrated electro-optic attention nonlinearities …
Transformers have transformed the field of natural language processing. This performance is largely attributed to the use of stacked self-attention layers, each of which consists of matrix multiplies as well as softmax operations. As a…
We introduce an electro-optic hardware platform for nonlinear activation functions in optical neural networks. The optical-to-optical nonlinearity operates by converting a small portion of the input optical signal into an analog electric…
Thin-film lithium niobate (TFLN) has been considered as one of the most important platforms for constructing high-performance photonic integrated devices such as electro-optic modulators, frequency combs, classical/quantum light sources,…
The self-attention mechanism distinguishes transformer-based large language models (LLMs) apart from convolutional and recurrent neural networks. Despite the performance improvement, achieving real-time LLM inference on silicon remains…
Linear attentions have shown potential for improving Transformer efficiency, reducing attention's quadratic complexity to linear in sequence length. This holds exciting promise for (1) training linear Transformers from scratch, (2)…
Recently Transformers have provided state-of-the-art performance in sparse matching, crucial to realize high-performance 3D vision applications. Yet, these Transformers lack efficiency due to the quadratic computational complexity of their…
In Transformer models, non-GEMM (non-General Matrix Multiplication) operations -- especially Softmax and Layer Normalization (LayerNorm) -- often dominate hardware cost due to their nonlinear nature. To address this, previous approximation…
The realization of integrated, high-speed ultraviolet (UV) modulation is pivotal for the advancement of quantum information processing, portable atomic clocks, and secure solar-blind communications. While mature photonic platforms have…
The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness. However, its role in transfer learning remains poorly understood. In this paper,…
While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such models from scratch remains prohibitively expensive. Inheriting weights from pretrained…
We demonstrate a low-loss integrated electro-optic Mach-Zehnder modulator in thin-film lithium tantalate at 737 nm, featuring a low half-wave voltage-length product of 0.65 V$\cdot$cm, an extinction ratio of 30 dB, low optical loss of 5.3…
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks, but their deployment is often constrained by substantial memory footprints and computational costs. While prior work has achieved…
The tradeoff between precision and performance in molecular simulations can nowadays be addressed by machine-learned force fields (MLFF), which combine \textit{ab initio} accuracy with force field numerical efficiency. Different from…
Recently integrated optics has become an intriguing platform for implementing machine learning algorithms and inparticular neural networks. Integrated photonic circuits can straightforwardly perform vector-matrix multiplicationswith high…
Nonlinear metasurfaces are multifunctional photonic elements that generate and control light, enabling multiple proof-of-principle applications, such as in nonlinear holography, beam shaping, and nanoscale sources of entangled photon pairs.…
Thin film lithium niobate (LN) has recently emerged as a playground for chip-scale nonlinear optics and leads to highly efficient frequency conversions from near infrared to near-visible bands. For many nonlinear and quantum photonics…
Lithium Niobate (LN) is an important nonlinear optical material. Here we demonstrate LN microdisk resonators that feature optical quality factor ~ 100,000, realized using robust and scalable fabrication techniques, that operate over a wide…
Mode-locked lasers (MLLs) are essential for a wide range of photonic applications, such as frequency metrology, biological imaging, and high-bandwidth coherent communications. The growing demand for compact and scalable photonic systems is…
High modulation efficiency and a compact footprint are critical for next-generation electro-optic (EO) modulators. We introduce a new class of non-resonant recirculating phase modulators (PMs) that boosts modulation efficiency by repeatedly…
Lithium Niobate (LN or just niobate) thin-film micro-photonic resonators have promising prospects in many applications including high efficiency electro-optic modulators, optomechanics and nonlinear optics. This paper presents free-standing…