ICML 2024

Meta Info

Homepage: https://icml.cc/Conferences/2024

Papers

Large Language Models (LLMs)

• Serving LLMs

  • HexGen: Generative Inference of Foundation Model over Heterogeneous Decentralized Environment [Personal Notes] [arXiv] [Code]

    • HKUST & ETH & CMU

      • Support asymmetric tensor model parallelism and pipeline parallelism under the heterogeneous setting (i.e., each pipeline parallel stage can be assigned with a different number of layers and tensor model parallel degree).

        • Propose a heuristic-based evolutionary algorithm to search for the optimal layout.

  • MuxServe: Flexible Spatial-Temporal Multiplexing for LLM Serving [arXiv] [Code]

    • CUHK & Shanghai AI Lab & HUST & SJTU & PKU & UC Berkeley & UCSD

    • Colocate LLMs considering their popularity to multiplex memory resources.

  • APIServe: Efficient API Support for Large-Language Model Inferencing [arXiv]

    • UCSD

• Benchmark

  • Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference [arXiv] [Demo]

    • UC Berkeley

• Speculative decoding

  • Online Speculative Decoding [arXiv]

    • UC Berkeley & UCSD & Sisu Data & SJTU

• Video generation

  • VideoPoet: A Large Language Model for Zero-Shot Video Generation [Paper] [Homepage]

    • Google & CMU

    • Employ a decoder-only transformer architecture that processes multimodal inputs – including images, videos, text, and audio.

    • The pre-trained LLM is adapted to a range of video generation tasks.

• Image retrieval

  • MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions [Paper] [Homepage] [Code]

    • OSU & Google DeepMind

    • Enable multimodality-to-image, image-to-image, and text-to-image retrieval.

References

• Google DeepMind at ICML 2024, 2024/07/19