Chenxi Wang

Orcid: 0009-0006-3611-0000

Affiliations:
  • Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
  • Tsinghua University, Beijing, China


According to our database1, Chenxi Wang authored at least 16 papers between 2024 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
The Cylindrical Representation Hypothesis for Language Model Steering.
CoRR, May, 2026

When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies.
CoRR, October, 2025

DyFlow: Dynamic Workflow Framework for Agentic Reasoning.
CoRR, September, 2025

Cross-Cultural Transfer of Commonsense Reasoning in LLMs: Evidence from the Arab World.
CoRR, September, 2025

SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models.
CoRR, May, 2025

ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models.
CoRR, May, 2025

Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs.
CoRR, May, 2025

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models.
CoRR, May, 2025

DyFlow: Dynamic Workflow Framework for Agentic Reasoning.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Under the Shadow of Babel: How Language Shapes Reasoning in LLMs.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Cross-Cultural Transfer of Commonsense Reasoning in LLMs: Evidence from the Arab World.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks.
Proceedings of the 31st International Conference on Computational Linguistics, 2025

Word Form Matters: LLMs' Semantic Reconstruction under Typoglycemia.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024
Autonomous Agents for Collaborative Task under Information Asymmetry.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024


  Loading...