7 papers
Backpropagated Output Momentum: Relocating Optimizer History from Parameters to Task Space
Yuchen Li, Zongqi Fan, Nguyen H. Tran +1
Optimizer momentum is usually stored as a parameter-sized moving average of past gradients, which makes history costly and fixes each past signal in the coordinates in which it was…
Q-BridgeNet: A Quantization Network for Cross-Lingual Sign Language Translation
Liqian Feng, Lintao Wang, Xiaochen Liu +5
Most sign language translation (SLT) methods focus on isolated native sign-spoken pairs (e.g., American Sign Language - English). Extending language-specific SLT models to multilin…
Universal Quartic Scaling Law for Kerr-Type Interactions: Projection-Law Factorization Across Nonlinear Quantum Platforms
Xiaochen Liu, Ken-Tye Yong
We present a rigorous derivation and numerical validation of a universal projection-law factorization for quartic nonlinear coupling rates across physically distinct platforms. The…
Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards
Senura Hansaja Wanasekara, Minh-Duong Nguyen, Xiaochen Liu +2
Generative modeling has become a central paradigm in protein research, extending machine learning beyond structure prediction toward sequence design, backbone generation, inverse f…
Unified Effective Field Theory for Nonlinear and Quantum Optics
Xiaochen Liu, Ken-Tye Yong
Predicting phenomena that mix few-photon quantum optics with strong field nonlinear optics is hindered by the use of separate theoretical formalisms for each regime. We close this…
A Unified Spectrum for Turbulence in Microfluidic Flow
Chit Yau Kuan, Xiaochen Liu, Yi-Ping Ho +1
We present a predictive master spectrum describing turbulence-like flows in microfluidic systems. Extending Pao's viscous-range closure, the model introduces (i) an adaptive inerti…
FOSS solution for Molecular Dynamics Simulation Automation and Collaboration with MDSGAT
Jai Geddes Nelson, Xiaochen Liu, Ken Tye Yong
The process of setting up and successfully running Molecular Dynamics Simulations (MDS) is outlined to be incredibly labour and computationally expensive with a very high barrier t…