Xiangyu Z

Xiangyu Z on Hugging Face Daily Papers: 14 papers, 6 in the top 3 of their day, 1,009 upvotes.

1. MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization 103 upvotes, #2 of 2025-10-10
2. GenExam: A Multidisciplinary Text-to-Image Exam 21 upvotes, #4 of 2025-09-18
3. InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency 170 upvotes, #1 of 2025-08-26
4. Intern-S1: A Scientific Multimodal Foundation Model 242 upvotes, #1 of 2025-08-22
5. MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents 28 upvotes, #3 of 2025-07-28
6. MM-IFEngine: Towards Multimodal Instruction Following 31 upvotes, #6 of 2025-04-11
7. Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing 67 upvotes, #3 of 2025-04-04
8. Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM 41 upvotes, #4 of 2025-03-19
9. VisualPRM: An Effective Process Reward Model for Multimodal Reasoning 31 upvotes, #7 of 2025-03-14
10. OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference 67 upvotes, #1 of 2025-02-26
11. Redundancy Principles for MLLMs Benchmarks 25 upvotes, #4 of 2025-01-27
12. Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language 9 upvotes, #16 of 2024-07-02
13. MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning 18 upvotes, #6 of 2024-06-26
14. MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding 27 upvotes, #7 of 2024-06-21

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.