Zhongyu Niu

3 papers · 2024–2025 · 3 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 ❓ The Questioner

Venues

ICLR (1) ICML (1) NeurIPS (1)

Top co-authors

Ruixuan Li (3) Wei Liu (3) Jun Wang (3) Zhiying Deng (3) Haozhao Wang (3) Zhigang Zeng (1) YuanKai Zhang (1) Lang Gao (1)

Research topics

Machine Learning (3) Artificial Intelligence (2) Core AI (2) Core Methods (2) Deep Learning (1) Natural Language Processing (1) Applications (1) Architectures (1) Learning Types (1) Optimization & Theory (1)

Keywords

causal inference (1) text classification (1) feature selection (1) rationale extraction (1) mutual information (1) cooperative game (1) weight matrix (1) sampling bia (1) low rank (1) maximum mutual information (1) generator (1) correlation (1) predictor (1) norms (1) rationales (1) rationalization (1)

Papers

Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets ICML 2025 Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization ICLR 2025 Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization NeurIPS 2024