A recurring pattern in "reasoning without training" is that base LLMs already assign non-trivial probability mass to correct multi-step solutions; the bottleneck is locating these modes efficiently at inference time. Power sampling provides a principled way to bias decoding toward such modes by targeting p_theta(x)^alpha with alpha > 1, but practical approximations must account for future-dependent correction factors that determine which prefixes remain promising.
We introduce Auxiliary Particle Power Sampling (APPS), a blockwise particle algorithm for approximating the sequence-level power target with a bounded population of partial solutions. APPS propagates hypotheses in parallel using proposal-corrected power reweighting and refines their survival through future-value-guided selection at resampling boundaries. This redistributes finite compute across competing prefixes rather than committing to a single unfolding path, while providing a direct scaling knob in the particle count and predictable peak memory. We instantiate the future-value signal with short-horizon rollouts and also study an amortized variant that replaces rollouts with a lightweight learned selection head. AMore broadly, APPS improves the accuracy--runtime trade-off of training-free decoding, further supporting the view that inference-time power approximation can recover gains often attributed to post-training.
Saliency Guided Longitudinal Medical Visual Question Answering
Dept. of Computer Science and Engineering University of California, San Diego（计算机科学与工程系，加州大学圣地亚哥分校）；Dept. of Radiology and Biomedical Imaging Yale University（放射学与生物医学成像系，耶鲁大学）
University of Pittsburgh（匹兹堡大学）；University of Minnesota - Twin Cities（明尼苏达大学-双城分校）；Colorado State University（科罗拉多州立大学）；University of Maryland, College Park（马里兰大学学院市分校）
AD-Net: Attention-based dilated convolutional residual network with guided decoder for robust skin lesion segmentation
COMSATS University Islamabad (CUI)（COMSATS大学伊斯兰堡校区）；University of Engineering and Technology (UET) Lahore（拉合尔工程技术大学）；University of New South Wales（新南威尔士大学）；IBADAT International University Islamabad（伊巴达特国际大学伊斯兰堡校区）
Task-guided cross-subject latent alignment: a multi-encoder-decoder VAE
Centre for Neural Circuits and Behaviour Department of Physiology Anatomy and Genetics University of Oxford（神经回路与行为中心 生理解剖与遗传学系 牛津大学）；Big Data Institute Nuffield Department of Medicine University of Oxford（大数据研究所 纳菲尔德医学系 牛津大学）
Teacher Encoder-Student Decoder Denoising Guided Segmentation Network for Anomaly Detection
School of Computer Science, Chengdu University of Information Science and Technology（成都信息科技大学计算机科学学院）；Purdue University（普渡大学）；University at Albany（阿尔巴尼大学）
Enhancing material behavior discovery using embedding-oriented Physically-Guided Neural Networks with Internal Variables
Aragón Institute of Engineering Research (I3A)（阿拉贡工程研究所（I3A））；Mechanical Engineering Department（机械工程系）；University of Zaragoza（萨拉戈萨大学）；Institute for Health Research Aragon (IISA)（阿拉贡健康研究所（IISA））；Nanjing Tech University（南京工业大学）；Department of Mechanical Engineering, Universidad Politécnica de Madrid (UPM)（马德里理工大学机械工程系）
