Xuchan Bao

6 papers · 2019–2025 · 4 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 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (18)

Venues

ICLR (2) NeurIPS (2) ICML (1) JMLR (1)

Top co-authors

Cem Anil (2) Jan Betley (2) Owain Evans (2) Anna Sztyber-Betley (2) Sageev Oore (1) Qiyang Li (1) Guodong Zhang (1) Sicong Huang (1) Roger Grosse (1) Roger B Grosse (1)

Research topics

Deep Learning (5) Machine Learning (4) Architectures (4) Artificial Intelligence (3) Core AI (3) Core Methods (2) Optimization & Theory · Machine Learning (2) Optimization & Theory · Deep Learning (2) Mathematics & Optimization (1) Learning Types (1) Models (1) Optimization (1)

Keywords

gradient descent (2) neural network optimization (2) game theory (1) principal component analysis (1) style transfer (1) convergence analysis (1) ai safety (1) convergence rate (1) iteration complexity (1) linear autoencoder (1) preference aggregation (1) stochastic game (1) first-order method (1) stochastic method (1) smooth game (1) integral quadratic constraint (1) backdoor detection (1) social welfare (1) principal component (1) voting system (1)

Papers

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs ICML 2025 Tell me about yourself: LLMs are aware of their learned behaviors ICLR 2025 A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints JMLR 2021 Learning to Elect NeurIPS 2021 Regularized linear autoencoders recover the principal components, eventually NeurIPS 2020 TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer ICLR 2019