Skip to main content
Search

University of Alabama at Birmingham

6 related articles

Subscribe to updates
  1. arXiv

    SAM 3 at 4-bit weights stops grabbing the wrong object: SPQ lifts RefCOCO hit rate from 42.1 to 72.5

    Quantizing SAM 3's image-encoder weights to 4 bits while keeping activations at 8 bits produces prompt-alignment drift: masks look plausible but land on the wrong object or lose the target across video frames. SPQ gives more calibration weight to parameters that affect text-concept scores, constrains feature error along low-variance residual directions, and folds a mean-error correction estimated from paired video rollouts into existing biases. Under W4A8, RefCOCO Pr@0.5 rises from 42.1 for PTQ4SAM to 72.5 while retaining 54.8 COCO mask AP, with no added inference operators.

  2. Reward the search, not just the answer: process supervision lifts retrieval recall and holds up out of domain

    Search agents for multi-hop information seeking are trained on step-level judgments of each search action instead of only on final-answer correctness. RAG-Gym casts search as a Markov decision process and compares architecture, parameter optimization and action evaluation, combining a reasoning-reflection architecture, preference optimization and critic-guided inference into Re2Search++. Trained on HotpotQA, it beats outcome-supervised baselines on the unseen Bamboogle benchmark with higher retrieval recall at comparable or fewer search steps, and a critic trained on Llama-3.1-8B raises GPT-4o-mini MedQA accuracy.

  3. Emergency crowding gets a six-hour warning: proactive capacity protocols cut time over threshold by up to about a fifth in simulation

    Full Capacity Protocols in emergency departments usually start only after crowding thresholds are crossed, yet hallway beds, temporary nurses and transfer restrictions take time to arrange. A discrete-event simulation evaluation embedded a machine learning model forecasting waiting-room counts six hours ahead into the emergency flow and used those forecasts to trigger the protocol early. Over a simulated year, early activation significantly shortened time above the crowding threshold and average protocol duration at all three threshold settings, while changes in average emergency length of stay and wait time were not statistically significant.

  4. Single-cell multi-omics integration changes its starting point: factorizing cell similarities instead of rebuilding molecular measurements

    Single-cell multi-omics integration must place cells into one representation when only some cells have both RNA and chromatin accessibility measured, a mosaic design. Mosaic Cell Relation Factorization (MCRF) skips rebuilding molecular measurements and instead computes similarities between cells, then factorizes those relations into cell factors plus a separate weight matrix per modality, with paired cells sharing one set of factors across RNA and ATAC. On scMultiSim simulations, MCRF had higher median NMI than UINMF in 22 of 36 original configurations and than MIDAS in 28, often with smaller variation across simulation replicates; on 102 newly generated larger datasets, UINMF and MIDAS had higher median ARI in all 24 configurations with four replicates.

  5. arXiv

    DPRD aligns ROI-masked displacement vectors so a student with ~5% of the teacher's parameters reaches 85.46% Dice on AMOS, edging out MedNeXt

    The work proposes Displacement-Preserving Relational Distillation (DPRD), which in nnU-Net aligns batch-wise pairwise displacement vectors on ROI-masked case-level embeddings with relational scale normalization, and on ISLES 2022 and AMOS 2022 lets students using about 5% of the teacher's parameters and about 3% of its FLOPs outperform Logits KD, FitNet, RKD, and CIRKD, reaching 85.46% Dice and 11.72 mm HD95 on AMOS.

  6. arXiv

    DCD raises compressed 3D MRI segmentation mDice from 63.60% to 68.51% on BraTS 2024 and to 73.95% on ISLES 2022 while cutting parameters from 101.9M to 6.4M

    The authors propose Detail Consistent Distillation (DCD), which applies a 3D discrete wavelet transform to teacher and student encoder features at every stage during training and aligns only the directional detail subband D (excluding the low-frequency approximation A and the most noise-prone extreme high-frequency band S) after inverse-wavelet reconstruction in the spatial domain, raising the mDice of a 4x channel-reduced student from 63.60% to 68.51% on BraTS 2024 and from 70.21% to 73.95% on ISLES 2022 with no inference-time overhead.

You’re all caught up