SOTAVerified

Collaborative Inference

In collaborative inference, a single inference task is performed by multiple models distributed on two or more (typically resource-constrained IoT) devices

Papers

Showing 1120 of 68 papers

TitleStatusHype
CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level RoutingCode1
MoE^2: Optimizing Collaborative Inference for Edge Large Language Models0
Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation0
Distributed Mixture-of-Agents for Edge Inference with Large Language ModelsCode0
GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance GroundingCode1
Distributed Collaborative Inference System in Next-Generation Networks and Communication0
CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge CollaborationCode0
Collaborative Inference over Wireless Channels with Feature Differential Privacy0
SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization0
Edge-device Collaborative Computing for Multi-view Classification0
Show:102550
← PrevPage 2 of 7Next →

No leaderboard results yet.