Xiangyu Z's picture

Xiangyu Z

PhoenixZ

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 18 days ago

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

upvoted an article 3 months ago

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

upvoted a paper 3 months ago

Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation

View all activity

Organizations

None yet

commented a paper 8 months ago

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

Paper • 2510.08540 • Published Oct 9, 2025 • 110 •

New activity in PhoenixZ/OmniAlign-V over 1 year ago

Add task categories

#1 opened over 1 year ago by

New activity in PhoenixZ/OmniAlign-V-DPO over 1 year ago

Add task categories and language to dataset card

#2 opened over 1 year ago by

commented a paper over 1 year ago

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference

Paper • 2502.18411 • Published Feb 25, 2025 • 74 •

commented a paper almost 2 years ago

MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning

Paper • 2406.17770 • Published Jun 25, 2024 • 19 •