1.6k citations · 1.8k across the 8 of their papers we have counts for
8 papers
TALAN: Task-Aligned Latent Adaptation Networks for Targeted Post-Training of Large Language Models
Chengkai Zhang, Ziteng Liu, Junpu Wang +4
Targeted post-training aims to improve reasoning, math, and code without degrading strengths. Low-rank adapters are efficient but task-global; activation interventions are input-aw…
Learning to Reconstruct Shapes from Unseen Classes
Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang +3
From a single image, humans are able to perceive the full 3D shape of an object by exploiting learned shape priors from everyday life. Contemporary single-image 3D reconstruction a…
Visual Object Networks: Image Generation with Disentangled 3D Representation
Jun-Yan Zhu, Zhoutong Zhang, Chengkai Zhang +4
Recent progress in deep generative models has led to tremendous breakthroughs in image generation. However, while existing models can synthesize photorealistic images, they lack an…
Learning Shape Priors for Single-View 3D Completion and Reconstruction
Jiajun Wu, Chengkai Zhang, Xiuming Zhang +3
The problem of single-view 3D shape completion or reconstruction is challenging, because among the many possible shapes that explain an observation, most are implausible and do not…
Seeing Tree Structure from Vibration
Tianfan Xue, Jiajun Wu, Zhoutong Zhang +3
Humans recognize object structure from both their appearance and motion; often, motion helps to resolve ambiguities in object structure that arise when we observe object appearance…
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
Xingyuan Sun, Jiajun Wu, Xiuming Zhang +5
We study 3D shape modeling from a single image and make contributions to it in three aspects. First, we present Pix3D, a large-scale benchmark of diverse image-shape pairs with pix…
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
Jiajun Wu, Chengkai Zhang, Tianfan Xue +2
We study the problem of 3D object generation. We propose a novel framework, namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic space…
A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding
Renqiao Zhang, Jiajun Wu, Chengkai Zhang +2
Humans demonstrate remarkable abilities to predict physical events in complex scenes. Two classes of models for physical scene understanding have recently been proposed: "Intuitive…