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 125 of 68 papers

TitleStatusHype
Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework0
Smaller, Smarter, Closer: The Edge of Collaborative Generative AI0
A Wireless Collaborated Inference Acceleration Framework for Plant Disease Recognition0
Towards Intelligent Edge Sensing for ISCC Network: Joint Multi-Tier DNN Partitioning and Beamforming Design0
Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices0
Speculative End-Turn Detector for Efficient Speech Chatbot Assistant0
G-Boost: Boosting Private SLMs with General LLMs0
Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference SystemsCode0
PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational AutoencodersCode0
DistrEE: Distributed Early Exit of Deep Neural Network Inference on Edge Devices0
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
Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Models0
Private Collaborative Edge Inference via Over-the-Air ComputationCode0
Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary DetectionCode1
LiveMind: Low-latency Large Language Models with Simultaneous InferenceCode1
Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.