Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
BigMac: Breaking the Pareto Frontier of Compute and Memory in Multimodal LLM Training
Zili Zhang, Chengxu Yang, Shenglong Zhang +8
Training multimodal large language models (MLLMs) is challenged by both model and data heterogeneity. Existing systems redesign the training pipeline to address these challenges, b…
cs.LG2025
Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
Qi Wang, Mian Wu, Yuyang Zhang +7
Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Des…
cs.LG2024
Open-World Reinforcement Learning over Long Short-Term Imagination
Jiajian Li, Qi Wang, Yunbo Wang +4
Training visual reinforcement learning agents in a high-dimensional open world presents significant challenges. While various model-based methods have improved sample efficiency by…