today local_bar

Lu Jiang

Principal Researcher, Apple

3 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

#4807 · Jiaming Han, Hao Chen, Yang Zhao, Hanyu Wang, Qi Zhao, Ziyan Yang, Hao He, Xiangyu Yue, Lu Jiang

We propose a text-aligned visual representation to unify both visual understanding and generation within a single MLLM.

UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?

#4318 · Yuanxin Liu, Rui Zhu, Shuhuai Ren, Jiacong Wang, Haoyuan Guo, Xu Sun, Lu Jiang

This work investigates whether MLLMs can be used as unified evaluator for AI-generated videos and proposes a benchmark to assess this ability.

Poster Session 2

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

#4302 · Shanchuan Lin, Ceyuan Yang, Hao He, Jianwen Jiang, Yuxi Ren, Xin Xia, Yang Zhao, Xuefeng Xiao, Lu Jiang

Real-time interactive streaming video generation. 24fps up to a minute long.