Tianqi Zhong
3 papers · 2023–2025 · 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
Top co-authors
Research topics
Keywords
controllable text generation
(2)
domain generalization
(1)
text generation
(1)
primal-dual optimization
(1)
out-of-distribution generalization
(1)
compositional generalization
(1)
total variation
(1)
language model
(1)
prefix tuning
(1)
multi-aspect control
(1)
attribute recombination
(1)
invariant risk minimization
(1)
decoding-time control
(1)
attribute distribution
(1)
adversarial learning
(1)
attribute collapse
(1)
Papers
Out-of-distribution Generalization for Total Variation based Invariant Risk Minimization
ICLR 2025
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
ACL 2024
Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation
EMNLP 2023