works on
agentic models 1knowledge-action infrastructure 1long-horizon reasoning 1mixture of experts 1multi-domain training 1

From the 1 of 44 linked papers with an AI index.

activity
20242026
most citedVLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models

3 citations · 4 across the 16 of their papers we have counts for

collaborators
Showing cs.DCShow all

1 paper · 1 filter

cs.DC2026

NanoCP: Request-Level Dynamic Context Parallelism for Data-Expert Parallel Decoding

Jiefei Chen, Binbin Lin, Jinming Ma +9

Modern serving systems for Mixture-of-Experts (MoE) models adopt hybrid data-expert parallelism: expert parallelism (EP) shards experts across GPUs to scale capacity, while data pa…