Yinmin Zhang

3d object detection (2) reinforcement learning (1) benchmark evaluation (1) reward modeling (1) offline reinforcement learning (1) policy optimization (1) sequential decision making (1) attention mechanism (1) autonomous driving (1) depth estimation (1) low-rank approximation (1) value function (1) motion generation (1) loss function (1) cooperative learning (1) cooperative multi-agent (1) kv cache (1) 3d bounding box (1) q-value estimation (1) error diagnosis (1)