4 papers
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…