collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

ProDVI: Programmatic Dynamics Priors for Value Network Initialization

Xinwei Liu, Junyuan Liang, Jianting Zhang +1

Deep Reinforcement Learning (RL) is notoriously sample inefficient. One contributing factor is that RL agents are typically initialized from scratch, forcing them to acquire task-r…

cs.LG2026

Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control

Xinwei Liu, Junyuan Liang, Jianting Zhang +1

Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly i…

cs.LG2026

NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning

Xinwei Liu, Junyuan Liang, Zicong Hong +2

Augmenting model-free reinforcement learning (RL) with representations learned through observation dynamics prediction (observation-predictive RL) can improve sample efficiency and…

cs.LG2026

DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge

Yuegui Huang, Zhiyuan Fang, Weiqi Luo +3

Despite the computational efficiency of MoE models, the excessive memory footprint and I/O overhead inherent in multi-expert architectures pose formidable challenges for real-time…

cs.LG2025

Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline

Zhiyuan Fang, Yuegui Huang, Zicong Hong +5

Mixture of Experts (MoE), with its distinctive sparse structure, enables the scaling of language models up to trillions of parameters without significantly increasing computational…