Changyuan Tian

Orcid: 0009-0004-0972-7078

Affiliations:
  • Chinese Academy of Sciences, Aerospace Information Research Institute, Key Laboratory of Target Cognition and Application Technology, Beijing, China
  • University of Chinese Academy of Sciences, School of Electronic, Electrical and Communication Engineering, Beijing, China


According to our database1, Changyuan Tian authored at least 16 papers between 2022 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention.
CoRR, May, 2026

HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning.
CoRR, March, 2026

Consistency and Invariance Guided Multi-View Hypergraph Learning for Robust Hyperedge Prediction.
ACM Trans. Knowl. Discov. Data, February, 2026

Rectify Evaluation Preference: Improving LLMs' Critique on Math Reasoning via Perplexity-aware Reinforcement Learning.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
Rectify Evaluation Preference: Improving LLMs' Critique on Math Reasoning via Perplexity-aware Reinforcement Learning.
CoRR, November, 2025

SoPerModel: Leveraging Social Perception for Multi-Agent Trajectory Prediction.
IEEE Trans. Geosci. Remote. Sens., 2025

PIPER: Benchmarking and Prompting Event Reasoning Boundary of LLMs via Debiasing-Distillation Enhanced Tuning.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

HyperMixer: Specializable Hypergraph Channel Mixing for Long-term Multivariate Time Series Forecasting.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024
Relation-Aware Multi-Pass Comparison Deconfounded Network for Change Captioning.
IEEE Trans. Circuits Syst. Video Technol., December, 2024

LollipopE: Bi-centered lollipop embedding for complex logic query on knowledge graph.
Neural Networks, 2024

Rethinking the Reversal Curse of LLMs: a Prescription from Human Knowledge Reversal.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023
Tackling higher-order relations and heterogeneity: Dynamic heterogeneous hypergraph network for spatiotemporal activity prediction.
Neural Networks, September, 2023

Hypergraph-Enhanced Textual-Visual Matching Network for Cross-Modal Remote Sensing Image Retrieval via Dynamic Hypergraph Learning.
IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens., 2023

Thinking Like an Expert: Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals.
CoRR, 2023

2022
Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information.
IEEE Trans. Geosci. Remote. Sens., 2022

MCRN: A Multi-source Cross-modal Retrieval Network for remote sensing.
Int. J. Appl. Earth Obs. Geoinformation, 2022


  Loading...