5 papers
Beyond One-Step Accuracy: State-Affine Latent Transition for Reliable Visual Planning
Boyuan Zhang, Yingjun Du, Xiantong Zhen +1
Joint-embedding world models enable visual planning by learning action-conditioned dynamics in latent space. Yet they are commonly trained for one-step prediction on encoded states…
The Promise of Time-Series Foundation Models for Agricultural Forecasting: Evidence from Commodity Prices
Le Wang, Boyuan Zhang
Forecasting agricultural markets remains challenging due to nonlinear dynamics, structural breaks, and sparse data. A long-standing belief holds that simple time-series methods out…
Variational Task Vector Composition
Boyuan Zhang, Yingjun Du, Xiantong Zhen +1
Task vectors capture how a model changes during fine-tuning by recording the difference between pre-trained and task-specific weights. The composition of task vectors, a key operat…
Treatment response as a latent variable
Christopher Tosh, Boyuan Zhang, Wesley Tansey
Scientists often need to analyze the samples in a study that responded to treatment in order to refine their hypotheses and find potential causal drivers of response. Natural varia…
Bayesian Estimation of Panel Models under Potentially Sparse Heterogeneity
Hyungsik Roger Moon, Frank Schorfheide, Boyuan Zhang
We incorporate a version of a spike and slab prior, comprising a pointmass at zero ("spike") and a Normal distribution around zero ("slab") into a dynamic panel data framework to m…