Chen Wang

DETECTING SENSITIVE INFORMATION VIA MACHINE LEARNING AGENTS

MULTI-INSTANCE GPU AWARE AUTOSCALING IN AI MODEL SERVICE

EFFICIENT ALLOCATION OF MULTI-INSTANCE GPU IN AI MODEL SERVICE

AUTOMATED SOURCE CODE GENERATION AND OPTIMIZATION USING LARGE LANGUAGE MODELS AND REINFORCEMENT LEARNING

CLUSTER INFRASTRUCTURE WITH ON-DEMAND ACTIVATION

Large Language Model-Enabled Artificial Intelligence-Based Virtual Interactive Reading Assistant

ARTIFICIAL INTELLIGENCE (AI) MULTI-AGENT FRAMEWORK

INTERACTIVE CONVERSATIONAL CHATBOT FOR ENHANCING COMMUNICATION SKILLS OF INDIVIDUALS WITH LANGUAGE DIFFICULTIES

ENERGY CONSUMPTION AWARE CREATION OF SOFTWARE CODE

SERVERLESS FUNCTIONAL ROUTING FOR LARGE LANGUAGE MODEL INFERENCE SERVICE

GENERATING PICTURE DESCRIPTION TASK IMAGES USING AI

METHOD FOR DATA TYPE DRIVEN FRONT-END RENDERING

SELECTIVE FILTERING OF DATA BASED ON DATA RULES

CLOUD NATIVE AUTO-LABELING SYSTEM TO TRAIN CODE GENERATION MODELS

CROSS-PLATFORM CHATBOT USER AUTHENTICATION FOR CHAT HISTORY RECOVERY

MANAGING INSTANCES OF SERVERLESS FUNCTIONS IN A CLOUD COMPUTING SYSTEM

VERIFIABLE MLOPS TO TRAIN ML MODELS ON AUTONOMOUS ENVIRONMENTS

IDENTIFYING VIRTUAL MACHINE CONFIGURATIONS FOR PERFORMANCE TUNING APPLICATIONS

SYNTHETIC DIGITAL TWIN FOR A PATIENT

Electroencephalograph Signal Generation Speech in a Generative Adversarial Network

REINFORCEMENT LEARNING POLICY SERVING AND TRAINING FRAMEWORK IN PRODUCTION CLOUD SYSTEMS

ENHANCING CHATBOTS THROUGH PROMPT-ENGINEERED LARGE LANGUAGE MODELS

OMNI-CHANNEL ARTIFICIAL INTELLIGENCE (AI) CHATBOT FOR MEDICAL DIAGNOSIS AND MEDICAL TREATMENT

DEPLOYING WORKLOADS IN A CLOUD COMPUTING SYSTEM BASED ON ENERGY EFFICIENCY

DECOUPLING POWER AND ENERGY MODELING FROM THE INFRASTRUCTURE

ALLOCATING COMPUTING RESOURCES USING A MACHINE LEARNING MODEL

MITIGATION OF GARBAGE COLLECTION OVERHEAD

CONTAINER RESOURCE AUTOSCALING BY CONTROL PLANE

Building Reliable and Fast Container Images

Mitigating temperature induced performance variation

ENERGY EFFICIENT COMPUTING WORKLOAD PLACEMENT

CLOUD CLUSTER STORAGE RESOURCE AUTOSCALER

SCHEDULER INCORPORATING THERMAL AWARENESS

CLUSTER INFRASTRUCTURE WITH ON-DEMAND ACTIVATION

Resource configuration based on energy expenditure

ENERGY AWARE DATA REPLICATION

DYNAMIC ANOMALY FORECASTING FROM EXECUTION LOGS

VISUAL QUESTION GENERATION WITH ANSWER-AWARENESS AND REGION-REFERENCE

Identifying harmful containers

Querying knowledge graphs with sub-graph matching networks

Rich descriptor framework to text generation using graphs and structural neural encoders

AUTOMATIC ONLINE LOG TEMPLATE MINING

Performance biased resource scheduling based on runtime performance

Reward-based admission controller for resource requests in the cloud