Jianwei Zhang

8

Papers

5

Total Citations

Papers (8)

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration

Multi-Modal Disordered Representation Learning Network for Description-Based Person Search

Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

FlightBERT++: A Non-autoregressive Multi-Horizon Flight Trajectory Prediction Framework