Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Rethinking Calibration for High-Sparsity LLM Pruning: From Single Sources to Capability Coverage
Hu Xu, Zhaolong Xing, Congcong Liu +5
Post-training LLM pruning relies on a small calibration set, usually chosen heuristically and judged by WikiText perplexity or by mean accuracy on general-domain commonsense benchm…
cs.LG2026
FlowTrain: Flow-Based Decoupled Training for Industrial-Grade Vision-Language Models
Zhida Jiang, Zhaolong Xing, Yang Pei +14
Industrial-grade distributed training of vision-language models (VLMs) remains far less efficient than that of unimodal LLMs. Existing solutions either follow a monolithic design t…
cs.LG2026
FlexMARL: Graph-Driven Rollout-Training Co-Design for LLM-Based Multi-Agent Reinforcement Learning
Zhida Jiang, Zhaolong Xing, Jiawei Lu +13
Despite algorithm-level innovations for multi-agent reinforcement learning (MARL), the underlying infrastructure for large-scale MARL remains underexplored. Existing training frame…