6 papers
VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction
Hongjin Ji, Guoyang Xia, Luoyang Sun +2
Test-time training (TTT) offers a lightweight way to adapt vision--language--action (VLA) policies from unlabeled deployment streams, but it remains difficult to use reliably in cl…
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
Guoyang Xia, Fengfa Li, Hongjin Ji +4
Vision-language-action models (VLAs) have recently advanced robotic manipulation, yet the effects of different robot-data pre-training paradigms remain difficult to compare because…
Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning
Filip KovaÄeviÄ, Hong Chang Ji, Denny Wu +2
It is folklore that reusing training data more than once can improve the statistical efficiency of gradient-based learning. While this phenomenon has been extensively studied in li…
Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling
Fengfa Li, Hongjin Ji, Yifeng Ding +2
The Mixture of Experts MoE architecture is highly promising for resource constrained on device deployments yet training these models from scratch incurs prohibitive costs Current m…
Optimal Estimation in Orthogonally Invariant Generalized Linear Models: Spectral Initialization and Approximate Message Passing
Yihan Zhang, Hong Chang Ji, Ramji Venkataramanan +1
We consider the problem of parameter estimation from a generalized linear model with a random design matrix that is orthogonally invariant in law. Such a model allows the design ha…
Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing
Yihan Zhang, Hong Chang Ji, Ramji Venkataramanan +1
We consider the problem of parameter estimation in a high-dimensional generalized linear model. Spectral methods obtained via the principal eigenvector of a suitable data-dependent…