109 citations · 132 across the 9 of their papers we have counts for
11 papers
IronMind: Scaling Humanoid Dexterous Manipulation via Camera-Space Ego-Centric Pretraining
Huimin Pan, Yufan Ren, Kunpeng Song +16
Egocentric human video offers a scalable data source for dexterous manipulation, yet using it to train humanoid robots presents two challenges: (1) an embodiment gap, as human hand…
Principal Steering Subspaces for Online Adaptation of Frozen Generative Robot Policies
Jialeng Ni, Nathan Zhao, Kunpeng Song
Generative robot policies provide expressive behavior priors, but updating a large diffusion or flow-matching model through online interaction is costly. Latent-space reinforcement…
Creative Image Generation with Diffusion Models
Kunpeng Song, Ahmed Elgammal
Creative image generation has emerged as a compelling area of research, driven by the need to produce novel and high-quality images that expand the boundaries of imagination. In th…
Llama Learns to Direct: DirectorLLM for Human-Centric Video Generation
Kunpeng Song, Tingbo Hou, Zecheng He +12
In this paper, we introduce DirectorLLM, a novel video generation model that employs a large language model (LLM) to orchestrate human poses within videos. As foundational text-to-…
MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation
Kunpeng Song, Yizhe Zhu, Bingchen Liu +3
In this paper, we present MoMA: an open-vocabulary, training-free personalized image model that boasts flexible zero-shot capabilities. As foundational text-to-image models rapidly…
Improving Tuning-Free Real Image Editing with Proximal Guidance
Ligong Han, Song Wen, Qi Chen +13
DDIM inversion has revealed the remarkable potential of real image editing within diffusion-based methods. However, the accuracy of DDIM reconstruction degrades as larger classifie…
Diffusion Guided Domain Adaptation of Image Generators
Kunpeng Song, Ligong Han, Bingchen Liu +2
Can a text-to-image diffusion model be used as a training objective for adapting a GAN generator to another domain? In this paper, we show that the classifier-free guidance can be…
Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis
Bingchen Liu, Yizhe Zhu, Kunpeng Song +1
Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images. In this paper, we study the f…
Self-Supervised Sketch-to-Image Synthesis
Bingchen Liu, Yizhe Zhu, Kunpeng Song +1
Imagining a colored realistic image from an arbitrarily drawn sketch is one of the human capabilities that we eager machines to mimic. Unlike previous methods that either requires…
TIME: Text and Image Mutual-Translation Adversarial Networks
Bingchen Liu, Kunpeng Song, Yizhe Zhu +2
Focusing on text-to-image (T2I) generation, we propose Text and Image Mutual-Translation Adversarial Networks (TIME), a lightweight but effective model that jointly learns a T2I ge…
Sketch-to-Art: Synthesizing Stylized Art Images From Sketches
Bingchen Liu, Kunpeng Song, Ahmed Elgammal
We propose a new approach for synthesizing fully detailed art-stylized images from sketches. Given a sketch, with no semantic tagging, and a reference image of a specific style, th…