shengwen Liang — accepted AI-conference papers

2026

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

Jinxin Yu, Xueqing Chen, Yudong Pan, Lian Liu, shengwen Liang, Huawei Li +2

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 0 Source ↗Scholar ↗

2025

QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation

Yaoyu Zhu, Di Huang, Hanqi Lyu, Xiaoyun Zhang, Chongxiao Li, Wenxuan Shi +13

NeurIPS 2025poster

Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification, such as software programming and mathematical problems. Extending RLVR to electronic design automation (EDA), especially automat…

Cited by 0 Source ↗Scholar ↗