Dongzhan Zhou

Venues

Frequent coauthors

Papers

1. Deep Research Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks
   AAAI 2026 ·

   Haiyuan Wan

   DBLP profile ↗ORCID search ↗
2. Mitigating Low-Quality Reasoning in MLLMs: Self-Driven Refined Multimodal CoT with Selective Thinking and Step-wise Visual Enhancement
   AAAI 2026 ·

   Chongjun Tu

   DBLP profile ↗ORCID search ↗
3. ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition
   ACL 2026 ·

   Yujie Liu

   DBLP profile ↗ORCID search ↗
4. A CLIP-Powered Framework for Robust and Generalizable Data Selection
   ICLR 2025 ·

   Suorong Yang

   DBLP profile ↗ORCID search ↗
5. Accelerating 3D Molecule Generative Models with Trajectory Diagnosis
   NeurIPS 2025 ·

   Zhilong Zhang

   DBLP profile ↗ORCID search ↗
6. Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models
   EMNLP 2025 ·

   Haonan He

   DBLP profile ↗ORCID search ↗
7. CFSSeg: Closed-Form Solution for Class-Incremental Semantic Segmentation of 2D Images and 3D Point Clouds
   ACM MM 2025 ·

   Jiaxu Li

   DBLP profile ↗ORCID search ↗
8. CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation
   ICCV 2025 ·

   Jianyu Wu

   DBLP profile ↗ORCID search ↗
9. Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
   NeurIPS 2025 ·

   Junchi Yu

   DBLP profile ↗ORCID search ↗
10. ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area
    AAAI 2025 ·

    Junxian Li

    DBLP profile ↗ORCID search ↗
11. Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
    CVPR 2025 ·

    Di Zhang

    DBLP profile ↗ORCID search ↗
12. LLaMA-Berry: Pairwise Optimization for Olympiad-level Mathematical Reasoning via O1-like Monte Carlo Tree Search
    NAACL 2025 ·

    Di Zhang

    DBLP profile ↗ORCID search ↗
13. LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents
    NeurIPS 2025 ·

    Rui Li

    DBLP profile ↗ORCID search ↗
14. MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search
    NeurIPS 2025 ·

    Zonglin Yang

    DBLP profile ↗ORCID search ↗
15. MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses
    ICLR 2025 ·

    Zonglin Yang

    DBLP profile ↗ORCID search ↗
16. MokA: Multimodal Low-Rank Adaptation for MLLMs
    NeurIPS 2025 ·

    Yake Wei

    DBLP profile ↗ORCID search ↗
17. Scaling Physical Reasoning with the PHYSICS Dataset
    NeurIPS 2025 ·

    Shenghe Zheng

    DBLP profile ↗ORCID search ↗
18. Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning
    NeurIPS 2025 ·

    Yuhao Zhou

    DBLP profile ↗ORCID search ↗
19. SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
    NeurIPS 2025 ·

    Weijian Mai

    DBLP profile ↗ORCID search ↗
20. When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training Acceleration
    ICML 2025 ·

    Suorong Yang

    DBLP profile ↗ORCID search ↗
21. LOCR: Location-Guided Transformer for Optical Character Recognition
    EMNLP 2024 ·

    Yu Sun

    DBLP profile ↗ORCID search ↗
22. Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes
    ECCV 2024 ·

    Yaoting Wang

    DBLP profile ↗ORCID search ↗