Skip to main content
Yanjiu Conference logo

Call for Papers – ICFMCEI 2027, Makassar

International Conference on Foundation Model Compression and Efficient Inference — ICFMCEI 2027

Dates

13–14 February 2027

Venue

Makassar, Indonesia

Field

Foundation Model Compression and Efficient Inference

Topics of ICFMCEI 2027

Original papers are invited in Foundation Model Compression and Efficient Inference. Submit by 12 January 2027.

Submit Your Paper

Topics include, but are not limited to:

Techniques for Model Compression

  • Pruning strategies for deep neural networks
  • Quantization methods for reducing model size
  • Knowledge distillation approaches for efficiency

Inference Optimization Methods

  • Accelerating inference using hardware-specific techniques
  • Batching strategies to improve throughput
  • Dynamic scheduling for resource management

Performance Metrics and Evaluation

  • Benchmarking compression effectiveness across models
  • Evaluating trade-offs between accuracy and inference speed
  • Criteria for assessing energy consumption in inference

Applications of Compressed Models

  • Deploying models in edge computing environments
  • Real-time inference for autonomous systems
  • Implementation in mobile devices for NLP tasks

Challenges in Foundation Models

  • Addressing robustness during and post-compression
  • Mitigating loss of critical model features
  • Handling domain transfer with compressed models

Important Dates

Conference opens in

00days
00hours
00min
00sec
  1. Step 1

    Submission Deadline

  2. Step 2

    Registration Deadline

  3. Step 3

    Conference Date

Download

Get the official templates and forms for ICFMCEI 2027. Use the latest versions when preparing your submission.

Peer Review Process

Follow each step from abstract submission to awards and recognition.

Yanjiuconference peer review process: 12 steps from abstract submission to awards and recognition

See You in Makassar This February

Present your research, meet peers from over 50 countries and help shape the future of Foundation Model Compression and Efficient Inference.