← Search

Huawei Li

7 accepted papers

2026

CacheEdit: Efficient Multi-round Image Editing via Adaptive Token-wise Reuse.

ICML 2026poster

Instruction-based image editing (IIE) is a vital tool for iterative content creation, enabling multi-round interactions that refine visual details while preserving cross-round consistency. However, this workflow is constrained by the compute-bound nature of Diffusion Transformers (DiTs): because DiT…

Cited by 0SourceScholar
2026

CircuitNet 3.0: A Multi-Modal Dataset with Task-Oriented Augmentation for AI-Driven Circuit Design

ICLR 2026poster

Integrated circuit (IC) designs require transforming high-level specifications into physical layouts, demanding extensive expertise and specialized tools, as well as months of time and numerous iterations. While Machine Learning (ML) has shown promise in various research domains, the lack of large-s…

Cited by 0SourcecodeScholar
2026

From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph

ICLR 2026poster

Despite significant evolution of CUDA programming and domain-specific libraries, effectively utilizing GPUs with massively parallel engines remains difficult. Large language models (LLMs) show strong potential in generating optimized CUDA code from sequential code. However, using LLMs in practice fa…

Cited by 0SourceScholar
2025

Bridging Layout and RTL: Knowledge Distillation based Timing Prediction

ICML 2025spotlight

Accurate and efficient timing prediction at the register-transfer level (RTL) remains a fundamental challenge in electronic design automation (EDA), particularly in striking a balance between accuracy and computational efficiency. While static timing analysis (STA) provides high-fidelity results thr…

2023

Gram-based Attentive Neural Ordinary Differential Equations Network for Video Nystagmography Classification

ICCV 2023poster

Video nystagmography (VNG) is the diagnostic gold standard of benign paroxysmal positional vertigo (BPPV), which requires medical professionals to examine the direction, frequency, intensity, duration, and variation in the strength of nystagmus on a VNG video. This is a tedious process heavily influ…

Cited by 7PDFcodeScholar
2022

SASH: Efficient secure aggregation based on SHPRG for federated learning

UAI 2022poster

To prevent private training data leakage in Federated Learning systems, we propose a novel secure aggregation scheme based on seed homomorphic pseudo-random generator (SHPRG), named SASH. SASH leverages the homomorphic property of SHPRG to simplify the masking and demasking scheme, which for each of…

Cited by 20SourcePDFScholar
2017

A regularized on-line sequential extreme learning machine with forgetting property for fast dynamic hysteresis modeling

IROS 2017poster

Piezoelectric ceramics(PZT)actuator has been widely used in flexure-guided nanopositioning stage because of their high resolution. However, it is quite hard to achieve high-rate precision positioning control because of the complex hysteresis nonlinearity effect of PZT actuator. Thus, an online RELM…

Cited by 2SourceScholar