Tinghui Zhu
I am a first-year Ph.D. student in Computer Science at University of California, Davis, a member of LUKA Group. I am fortunate to be advised by Prof. Muhao Chen. Before that, I received my Master degree from Fudan University in 2025 and my Bachelor degree from Fudan University in 2022.
My research interests are broadly in Natural Language Processing and Multimodality, focusing on Reasoning, Planning, and Agent across different modalities.
Besides research, I enjoy swimming🏊♂️, basketball🏀, bowling🎳, tennis🎾 and piano🎹.
News
| Jun 15, 2026 |  I start my summer internship at Google Deepmind! |
|---|---|
| May 13, 2026 |  New paper on RLVR for video reasoning. Check Video Models Can Reason with Verifiable Rewards! |
| May 13, 2026 | New paper on improving alignment between video and audio. Check When Vision Speaks for Sound! |
| Apr 16, 2026 | New paper on mitigating redundancy in long visual reasoning. Check Adaptive Visual Reasoning! |
| Apr 05, 2026 | Our paper Can LLMs Learn to Map the World from Local Descriptions? is accepted to ACL 2026! |
| Dec 10, 2025 | New papers: Be my eyes on extending modality through multi-agent collaboration and omni-modal guardrail! |
| Aug 20, 2025 | Our paper MciteBench: A Benchmark for Multimodal Citation Text Generation in MLLMs is accepted to EMNLP 2025! |
| Jun 02, 2025 | New paper on analyzing current modality extension methods on omni-modal models! |
| May 27, 2025 | New paper on constructing global understanding from global descriptions! |
| Mar 04, 2025 | New paper on multimodal citation benchmark for MLLMs! |
| Oct 04, 2024 | New paper on cross-modality parametric knowledge conflicts in LVLMs! |
| Sep 21, 2024 | Our survey on role-playing language agents is accepted to TMLR! |
| Jul 10, 2024 | Our papers Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning and How Easily do Irrelevant Inputs Skew the Responses of Large Language Models? are accepted to COLM 2024! |
| Jun 07, 2024 | Our paper TravelPlanner: A Benchmark for Real-World Planning with Language Agents is accepted to ICML 2024 as a spotlight! |
| Apr 28, 2024 | New survey From Persona to Personalization: A Survey on Role-Playing Language Agents! |
| Apr 04, 2024 | New preprint How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?! |
| Feb 02, 2024 | New preprint TravelPlanner: A Benchmark for Real-World Planning with Language Agents! |
| Jan 31, 2024 | New preprint Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning! |
| Oct 09, 2023 |  I am awarded National Scholarship for Graduate Excellence! |
| Jul 26, 2023 | Our paper Towards Visual Taxonomy Expansion is accepted to ACMMM 2023! |
Selected Publications
-
Video Models Can Reason with Verifiable RewardsarXiv preprint arXiv:2605.15458, 2026 -
Is Extending Modality The Right Path Towards Omni-Modality?arXiv preprint arXiv:2506.01872, 2025 -
Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language ModelsarXiv preprint arXiv:2410.03659, 2024 -
Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought ReasoningCOLM, 2024 -
Towards Visual Taxonomy ExpansionProceedings of the 31st ACM International Conference on Multimedia, 2023
