UltraEP is the first exact-load real-time expert balancer for large-EP MoE training and serving on rack-scale nodes, reaching 94.3% of ideal throughput and 1.49x over no-balancing.
ZKML: An Optimizing System for ML Inference in Zero-Knowledge Proofs
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
ForeMoE uses routing foresight from the rollout stage to enable micro-step load balancing in MoE RL post-training via a hierarchical planner and transfer engine, claiming up to 1.45x speedup on 64 GPUs.
The paper introduces certified virtual cuts and proves per-key replay equality for wellformed DBLog runs, with all proofs machine-checked in Isabelle/HOL.
The paper delivers a systematization of knowledge on AI agent-blockchain interactions via a bidirectional trust framework, an Agent-Blockchain Interaction Model, a five-dimensional evaluation lens, and nine identified open problems.
ZKMLOps is an MLOps framework that uses zero-knowledge proofs to generate verifiable cryptographic evidence of AI model compliance without revealing confidential information.
Proposes referential security as a paradigm for AI evaluations that reframes model identity as verifiable to support reproducible audits and regulatory decisions despite system changes.
citing papers explorer
-
Toward Web 4.0: Bidirectional Trust between AI Agents and Blockchain
The paper delivers a systematization of knowledge on AI agent-blockchain interactions via a bidirectional trust framework, an Agent-Blockchain Interaction Model, a five-dimensional evaluation lens, and nine identified open problems.