Skip to content
conftrace_

Lichuan Xiang

7 papers · 2023–2026 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🏆 Grand Slam ❓ The Questioner

Venues

ICML (2) AAAI (1) AutoML (1) CVPR (1) ICLR (1) NeurIPS (1)

Top co-authors

Hongkai Wen (7) Hoang Pham (2) Long Tran-Thanh (2) Zheng Fang (2) Xu Cai (2) Łukasz Dudziak (2) Bing Wang (1) Kaicheng Zhou (1) Lukasz Dudziak (1) Thomas Chau (1)

Research topics

Machine Learning (6) Deep Learning (5) Application Areas (5) Optimization & Theory · Machine Learning (4) Artificial Intelligence (3) Models (3) Computer Vision (2) Generation (2) Learning Paradigms (2) Architectures (1) Core AI (1) Optimization & Theory · Deep Learning (1) Techniques (1)

Keywords

neural architecture search (2) pruning at initialization (2) diffusion model (2) model compression (2) text-to-image generation (1) neural network optimization (1) gradient-based method (1) hierarchical generative model (1) multi-objective optimization (1) differentiable optimization (1) controllable generation (1) image fidelity (1) search space (1) sparse network (1) network topology (1) gating mechanism (1) differentiable architecture search (1) architecture optimization (1) graph similarity (1) zero-cost proxy (1)

Papers

DynFusion: Rethinking Condition Fusion for Adaptive Multi-Conditional Text-to-Image Generation CVPR 2026 DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle ICLR 2025 FlexControl: Computation-Aware Conditional Control with Differentiable Router for Text-to-Image Generation ICML 2025 Towards Neural Architecture Search through Hierarchical Generative Modeling ICML 2024 Exploiting Network Compressibility and Topology in Zero-Cost NAS AutoML 2023 Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask? NeurIPS 2023 Zero-Cost Operation Scoring in Differentiable Architecture Search AAAI 2023