6 papers
NOVA-CIM: Noise- and Correlation-Tolerant Stochastic Interfaces for Analog Compute-in-Memory
Jiachen Ren, Wenshuai Yao, Haobo Liu +6
Analog compute-in-memory (CIM) enables energy-efficient model acceleration, but its reliance on ADC-based readout, which directly quantizes noisy column currents, makes inference a…
FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy
Qingyao Yang, Runming Yang, He Xiao +7
While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specializ…
Split CNN Inference on Networked Microcontrollers
Junyu Lu, Shashwath Suresh, Hao Liu +2
Running deep neural networks on microcontroller units (MCUs) is severely constrained by limited memory resources. While TinyML techniques reduce model size and computation, they of…
Practical Scaling Laws: Converting Compute into Performance in a Data-Constrained World
Christopher M. Bryant, Hao Liu
The scaling laws guiding modern model training were calibrated for a single regime: data-rich, single-epoch pretraining. The dominant such scaling law form, Chinchilla's $L = E + A…
Inverse Design of Multi-Layer Sub-Pixel-Resolution RF Passives Through Grayscale Diffusion with Flexible S-Parameter Conditioning
Tommaso Dreossi, Christopher M. Bryant, Hao Liu +4
Inverse design of RF passive components from S-parameters is a high-dimensional, ill-posed problem, and prior generative approaches are limited to single-layer binary-metallization…
Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models
He Xiao, Qingyao Yang, Dirui Xie +7
Large language models with billions of parameters are often over-provisioned: many layers contribute little unique information yet dominate the memory and energy footprint during i…