α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Dongzhi Jiang
Dongzhi Jiang
8
papers
801
total citations
papers (8)
MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
ECCV 2024
arXiv
498
citations
T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
NEURIPS 2025
arXiv
100
citations
MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
ICML 2025
arXiv
94
citations
Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction
ICCV 2023
arXiv
56
citations
MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
NEURIPS 2025
arXiv
24
citations
EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
ICML 2025
arXiv
20
citations
MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines
ICLR 2025
7
citations
BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
NEURIPS 2025
arXiv
2
citations