Zhenpeng Huang
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
arXiv 2026
N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models
arXiv 2025
p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
arXiv 2024
VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model
arXiv 2024
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers