1 citations · 1 across the 6 of their papers we have counts for
7 papers
GeoBridge: Evolving Transferable Decoder Topologies for Geometric Vision
Rui Wang, Haoyu Zhang, Ran Cheng
Depth estimation and Gaussian reconstruction share a need for multi-scale feature processing, yet use different prediction interfaces and training objectives. Whether a decoder's i…
VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement
Wenzhuo Xu, Yuchen Zhu, Chongjian Ge +8
Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of indicating the obligation a clip violates or the moment it f…
VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing
Kijung Jeon, Thuy-Duong Vuong, Molei Tao
Inference-time scaling is a promising paradigm to improve generative models, especially when outputs must satisfy structural constraints or optimize downstream rewards. We consider…
Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing
Kijung Jeon, Michael Muehlebach, Molei Tao
Generative modeling within constrained sets is essential for scientific and engineering applications involving physical, geometric, or safety requirements (e.g., molecular generati…
NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
Fang Wu, Haokai Zhao, Da Xing +18
Training a diffusion model involves two sources of randomness for each data sample: the timestep and the Gaussian noise realization. The timestep has been studied extensively throu…
How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?
Kuo-Wei Lai, Guanghui Wang, Molei Tao +1
Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima. The implicit bias refers to the limiting g…
Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models
Xinxi Zhang, Song Wen, Ligong Han +6
Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by…