6 papers
OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
Hongyu Liu, Chun Wang, Feng Gao +6
We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR video generators can produce…
RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
Xuelu Feng, Yunsheng Li, Ziyu Wan +4
Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key challenge, however, lies in desi…
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Dong Chen, Fangyun Wei, Ziyu Wan +18
We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters acro…
AvatarPointillist: AutoRegressive 4D Gaussian Avatarization
Hongyu Liu, Xuan Wang, Zijian Wu +7
We introduce AvatarPointillist, a novel framework for generating dynamic 4D Gaussian avatars from a single portrait image. At the core of our method is a decoder-only Transformer t…
MorphoSim: An Interactive, Controllable, and Editable Language-guided 4D World Simulator
Xuehai He, Shijie Zhou, Thivyanth Venkateswaran +4
World models that support controllable and editable spatiotemporal environments are valuable for robotics, enabling scalable training data, repro ducible evaluation, and flexible t…
VLM4D: Towards Spatiotemporal Awareness in Vision Language Models
Shijie Zhou, Alexander Vilesov, Xuehai He +7
Vision language models (VLMs) have shown remarkable capabilities in integrating linguistic and visual reasoning but remain fundamentally limited in understanding dynamic spatiotemp…