3 papers
cs.LG2026
SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
Haoyu Huang, Boyu Liu, Linlin Yang +6
The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevai…
cs.LG2026
Circuit-Inspired High-Order Neural Networks with Unified Neural Dynamics Modeling for PDE Solving and Visual Perception
Tongfei Chen, Jingying Yang, Linlin Yang +8
Deep networks often rely on architectural heuristics to shape representation evolution, limiting their ability to model data governed by intrinsic dynamics. We present the Circuit-…
cs.LG2025
Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method
Qingcheng Zhu, Yangyang Ren, Linlin Yang +6
Deploying large language models (LLMs) is challenging due to their massive parameters and high computational costs. Ultra low-bit quantization can significantly reduce storage and…