Xinyan Chen

Orcid: 0009-0003-8475-962X

Affiliations:
  • Chinese University of Hong Kong, Hong Kong
  • University of Science and Technology of China, Hefei, China (former)
  • Peking University, School of Computer Science, State Key Laboratory of Multimedia Information Processing, Beijing, China (former)


According to our database1, Xinyan Chen authored at least 9 papers between 2023 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both.
CoRR, May, 2026

MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints.
CoRR, March, 2026

2025
Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation.
CoRR, November, 2025

Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark.
CoRR, October, 2025

MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning.
CoRR, June, 2025

EmpathyAgent: Can Embodied Agents Conduct Empathetic Actions?
CoRR, March, 2025

MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024
Learning from Mistakes: Iterative Prompt Relabeling for Text-to-Image Diffusion Model Training.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023
Iterative Prompt Relabeling for diffusion model with RLDF.
CoRR, 2023


  Loading...