conftrace_

Xize Liang

4 papers · 2023–2025 · 2 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 · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

ICLR (2) ICML (2)

Top co-authors

Jie Wang (4) Feng Wu (2) Hanzhu Chen (2) Zhihao Shi (2) Lin Yang (1) Shuang Qiu (1) Zhiwei Zhuang (1) Yue Wu (1) Chao Chen (1) Zhihang Fu (1)

Research topics

Machine Learning (4) Artificial Intelligence (2) Deep Learning (2) Application Areas (2) Architectures (2) Core AI (2) Optimization & Theory (2) Natural Language Processing (1) Learning Paradigms (1) Learning Types (1) Resources & Methods (1)

Keywords

graph neural network (2) large language model (2) message passing (2) preference alignment (1) noise tolerance (1) convergence guarantee (1) rejection sampling (1) subgraph sampling (1) fine tuning (1) robust loss (1) mini-batch gradient (1) neighbor explosion (1) curriculum (1) interaction (1) iterative paradigm (1) sample efficiency (1) evolving (1) scalable learning (1) transductive learning (1)

Papers

Accurate and Scalable Graph Neural Networks via Message Invariance ICLR 2025 Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between Samples ICML 2025 ROPO: Robust Preference Optimization for Large Language Models ICML 2025 LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence ICLR 2023