huggingface.daily_papers

curl "https://api.onekey.dev/v1/huggingface/daily_papers" \
  -H "x-api-key: YOUR_API_KEY"

{
  "success": true,
  "data": [
    {
      "content": {
        "id": "2609.26333",
        "title": "Disaggregated Quantization: Specializing LLM Prefill and Decode",
        "text": "Prefill and decode reward different approaches to quantization: low-precision arithmetic accelerates prompt processing, while compact weights reduce memory traffic during generation. We propose \"disaggregated quantization\" (DQ), which specializes computation formats, weights and storage placement to both of these phases. On Qwen 3 and Gemma 3, removing activation quantization specifically on decode improves accuracy on decode-heavy tasks without increasing inference cost. Training separate compute-native prefill weights accelerates prompt processing relative to weight-only inference while matching or exceeding its accuracy at 2-3-bit decode on both decode-heavy and prefill-heavy tasks. With released Qwen3.8-27B GGUF decoders, training an NVFP4 prefiller improves 1-bit accuracy by 32.5 points on MMLU-Pro and 35.3 on MMMU-Pro without modifying the decode checkpoint. To accommodate the additional checkpoint on a single device, offloaded disaggregated prefill (ODP) streams its weights from SSD, amortizing loading over prompt length. On the same 27B model, ODP delivers a 1.78x time-to-first-token speedup over the weight-only baseline at 8K prompt length in llama.cpp. We evaluate accuracy under disaggregated serving in vLLM and further validate shared-weight format disaggregation through post-training quantization on models up to 2.8T parameters.",
        "createdAt": "2026-09-21T20:00:00Z"
      },
      "engagement": {
        "likes": 23,
        "comments": 1
      },
      "package": {
        "repositoryUrl": "https://github.com/IST-DASLab/disaggregated-quantization"
      },
      "media": {
        "thumbnailUrl": "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2609.26333.png"
      }
    },
    {
      "content": {
        "id": "2609.28327",
        "title": "LightMIS: Ultra-Lightweight Medical Image Segmentation Without a Stage-Wise Decoder",
        "text": "We present LightMIS, a scalable family of ultra-lightweight convolutional networks for 2D binary medical image segmentation without a learned stage-wise decoder. LightMIS aligns the outputs of a five-level encoder to a common resolution using Scale-Aligned Projection blocks, aggregates them once, and refines the fused representation with an Adaptive Fusion Cascade. The cascade combines Adaptive Kernel Fusion with the proposed Progressive Receptive Fusion module, which uses temporary channel expansion, complementary depthwise receptive fields, and progressive cross-branch information transfer. We evaluate LightMIS-T, LightMIS-S, and LightMIS using five-fold cross-validation under a common nnU-Net v2.3.1 protocol on DRIVE, Kvasir-SEG, DSB18, BUSI, ISIC-2017, and ISIC-2018. Full LightMIS contains 0.131 M parameters and requires 0.575 GFLOPs for a 3times256times256 input, achieving modality-macro Dice and IoU scores of 86.71% and 78.99%, respectively. Mobile U-ViT obtains 86.75% Dice and 79.07% IoU, so the observed differences are 0.04 and 0.08 percentage points. Relative to Mobile U-ViT, nnWNet, and nnU-Net, LightMIS reduces parameter count by 90.58-99.61% and GFLOPs by 82.54-96.14%. On an Arm Mali-G52 MC2 GPU, all LightMIS variants achieve full GPU delegation, with median delegated latency ranging from 53.31 ms for LightMIS-T to 138.31 ms for LightMIS. These results demonstrate a favorable accuracy-complexity trade-off and on-device execution feasibility for the evaluated tasks",
        "createdAt": "2026-09-23T20:00:00Z"
      },
      "engagement": {
        "likes": 2,
        "comments": 1
      },
      "package": {
        "repositoryUrl": "https://github.com/AndreiiArhire/LightMIS"
      },
      "media": {
        "thumbnailUrl": "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2609.28327.png"
      }
    }
  ],
  "metadata": {
    "platform": "huggingface",
    "endpoint": "daily_papers",
    "cached": false,
    "stale": false,
    "age_s": 0,
    "fetched_at": "2026-01-01T12:00:00+00:00",
    "credits_charged": 5,
    "request_id": "7f3a9c2e5b1d4c8fa2e6d0b9c4f18e37"
  },
  "error": null
}