Skip to main content
Search

# Echo

2 related articles

Subscribe to updates
  1. arXiv

    Tensor-parallel traffic drops to 4 bits: Echo feeds each rounding error into later calls, beating NCCL by 2.09x on 1 GB messages

    Echo turns the tensor-parallel all-reduce into 4-bit transport with a high-precision sum and feeds each rounding error back into later calls so the accumulated error stays bounded with depth, running 2.09x faster than the 16-bit NCCL all-reduce on 1 GB messages while Qwen3-8B stays within 0.4 points of 16-bit inference across seven benchmarks.

    National University of SingaporePeking University
    Xingyu Xie（First author）
    EchoQuantized all-reduceError feedbackTensor parallelismLow-bit quantization
  2. arXiv

    ECHO-k uses a foundation model's internal representations as self-supervised proxy targets to select modalities sequentially under budget and improve downstream performance when the task is unknown

    The work introduces ECHO-k, a task-agnostic and self-supervised principle for modality acquisition that uses a deep model's internal pretrained representations (e.g., from a foundation model) as proxy targets summarizing cross-modal information, provides theoretical guarantees in a stylized linear setting that motivate a reinforcement learning policy for sequential modality selection, and, across task-agnostic and label-free acquisition baselines, consistently improves budgeted downstream performance across diverse foundation-model backends.

    Eeshaan Jain（First author）
    EchoTest-Time Feature AcquisitionSelf-Supervised LearningReinforcement Learning

You’re all caught up