Changyuan Tian
4 papers · 2024–2026 · 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
🗺️
Taxonomy Completionist
(16)
Top co-authors
Research topics
Machine Learning
(4)
Natural Language Processing
(3)
Artificial Intelligence
(2)
Deep Learning
(2)
Applications
(2)
Core AI
(2)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Data Science & Analytics
(1)
Generation
(1)
Methods
(1)
Optimization & Theory
(1)
Resources & Methods
(1)
Keywords
large language model
(2)
mathematical reasoning
(1)
knowledge distillation
(1)
knowledge representation
(1)
contextual reasoning
(1)
instruction tuning
(1)
message passing
(1)
time series forecasting
(1)
multivariate time series
(1)
benchmark dataset
(1)
supervised fine-tuning
(1)
reversal curse
(1)
channel correlation
(1)
long-term forecasting
(1)
event reasoning
(1)
group relative policy optimization
(1)
relationship reasoning
(1)
channel mixing
(1)
solution verification
(1)
contextual faithfulness
(1)
Papers
Rectify Evaluation Preference: Improving LLMs’ Critique on Math Reasoning via Perplexity-aware Reinforcement Learning
AAAI 2026
HyperMixer: Specializable Hypergraph Channel Mixing for Long-term Multivariate Time Series Forecasting
AAAI 2025
PIPER: Benchmarking and Prompting Event Reasoning Boundary of LLMs via Debiasing-Distillation Enhanced Tuning
ACL 2025
Rethinking the Reversal Curse of LLMs: a Prescription from Human Knowledge Reversal
EMNLP 2024