3 papers
cs.LG2026
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
Peihao Wang, Shan Yang, Xijun Wang +8
Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability…
cs.RO2024
Deep Stochastic Kinematic Models for Probabilistic Motion Forecasting in Traffic
Laura Zheng, Sanghyun Son, Jing Liang +3
In trajectory forecasting tasks for traffic, future output trajectories can be computed by advancing the ego vehicle's state with predicted actions according to a kinematics model.…
cs.CV2023
ViLA: Efficient Video-Language Alignment for Video Question Answering
Xijun Wang, Junbang Liang, Chun-Kai Wang +4
In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unifi…