Publications (18)
MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction
Xiao Hu, Eric Liu, Weizhou Wang +2
Retrieval-Augmented Generation (RAG) offers a solution to mitigate hallucinations in Large Language Models (LLMs) by grounding their outputs to knowledge retrieved from external so…
Molecular Axis Distribution Moments in Ultrafast Transient Absorption Spectroscopy: A Path Towards Ultrafast Quantum State Tomography
Shashank Kumar, Eric Liu, Liang Z. Tan +2
In ultrafast experiments with gas phase molecules, the alignment of the molecular axis relative to the polarization of the interacting laser pulses plays a crucial role in determin…
Memory-Guided Unified Hardware Accelerator for Mixed-Precision Scientific Computing
Chuanzhen Wang, Leo Zhang, Eric Liu
Recent hardware acceleration advances have enabled powerful specialized accelerators for finite element computations, spiking neural network inference, and sparse tensor operations…
Hindsight Logging for Model Training
Rolando Garcia, Eric Liu, Vikram Sreekanti +5
In modern Machine Learning, model training is an iterative, experimental process that can consume enormous computation resources and developer time. To aid in that process, experie…
Active pulsatile gels: from chemical microreactor to polymeric actuator
Baptiste Blanc, Zhenkun Zhang, Eric Liu +5
We report on a synthesis protocol, experimental characterization and theoretical modeling of active pulsatile Belousov-Zhabotinsky (BZ) hydrogels. Our two-step synthesis technique…
MotionScript: Natural Language Descriptions for Expressive 3D Human Motions
Payam Jome Yazdian, Rachel Lagasse, Hamid Mohammadi +3
We introduce MotionScript, a novel framework for generating highly detailed, natural language descriptions of 3D human motions. Unlike existing motion datasets that rely on broad a…