5 papers
TableVision: Recovering Verified Structure from Historical Tables
Todd Y. Zhou, James M. Snyder
Gaps, skips, and mistakes are the normal state of a historical register: rows go missing, tables cross page breaks, columns slip under wrong names, and column sums disagree with th…
Learning Counterfactual World Models for Embodied Reasoning under Partial Observability
Todd Y. Zhou, Daniel Zhang
World models promise a general route to embodied intelligence: learn predictive dynamics once, then reason, plan, and act with them. Increasingly, the representations beneath such…
When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion
Todd Zhou
Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling. We study this pass@k inversion: after trai…
Beyond Motion Primitives: Behavioral Activity Recognition from Head-Mounted IMU
Chung-Ta Huang, Leopold Das, Jeffrey Zhou +10
AR smart glasses need continuous behavioral context to offer proactive assistance, yet their most practical always-on sensor, the head-mounted Inertial Measurement Unit (IMU), dete…
Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
Advaith Ravishankar, Serena Liu, Mingyang Wang +11
State-of-the-art text-to-image models produce high-quality images, but inference remains expensive as generation requires several sequential ODE or denoising steps. Native one-step…