The paper introduces Spatial‑FAD, a few‑shot medical anomaly detection framework that fuses Vision‑Language Model (CLIP) semantics with spatial priors from Vision Foundation Models (DINO). A VFM‑enhanced adapter injects structural affinity into CLIP features, while a sliding‑window aggregation produces high‑resolution embeddings for finer lesion localization. Prototype‑enhanced support memory further improves efficiency and performance, yielding significant gains on Liver CT, Retinal OCT, and Brain MRI datasets, notably an 11.4% Dice improvement in 4‑shot scenarios.
By Juzheng Miao, Yuchen Yuan, Cheng Chen, Pheng-Ann Heng
DenseTRF is a self‑supervised framework that adapts texture‑aware representations for dense prediction in surgical computer vision. It uses slot attention to learn invariant visual structures and then conditions dense prediction on these representations, merging models to adapt to target distributions without supervision. Experiments on multiple surgical procedures show that DenseTRF improves cross‑distribution generalization compared to state‑of‑the‑art segmentation models and test‑distribution adaptation methods.
By Guiqiu Liao, Matja\v{z} Jogan, Daniel A. Hashimoto
General-purpose object detectors lose accuracy on UAV footage, where targets span only a handful of pixels and onboard compute is limited. Prior work composes independently-validated architectural tec...
ActMap is a new white‑box representation that compresses the entire hidden‑state trajectory of a language model during generation into a fixed 12 × 32 × 128 tensor. This compact 96 KiB map can be captured with no overhead and is read by a lightweight Vision Transformer to estimate answer correctness in a fraction of a millisecond. In experiments on short‑answer QA, math, and summarization, ActMap outperforms sampling, token‑probability, attention, and embedding baselines and matches a larger ACT‑ViT detector while achieving lower calibration error on most test pairs.
By Jacopo Dardini (University of Bologna), Roberta Calegari (University of Bologna)
The paper introduces Calibration-Aware Uncertainty Cascades (CAUC), a post‑hoc framework that calibrates each model’s confidence independently and uses these calibrated scores to decide when to accept an early prediction, invoke a stronger model, or combine outputs. CAUC establishes a common reliability scale across heterogeneous models, decoupling deployment policies from specific model pools or budgets. Experiments on six language benchmarks show a 1.9% relative accuracy gain over strong‑model‑only inference while cutting strong‑model calls by about 47%, and on image classification it maintains or improves performance while reducing GFLOPs by up to 57%.
By Yilin Zhang, Han Jiang, Cai Xu, Ying Liu, Wei Zhao
Dream4D is a new framework for generating spatiotemporally coherent 4D content. It uses a two‑stage pipeline: first, few‑shot learning predicts optimal camera trajectories from a single image; second, a pose‑conditioned diffusion process creates geometrically consistent multi‑view sequences that are converted into a persistent 4D representation. The method uniquely combines rich temporal priors from video diffusion models with geometric awareness from reconstruction models, achieving higher quality metrics such as mPSNR and mSSIM compared to existing approaches.
By Xiaoyan Liu, Kangrui Li, Jiaxin Liu, Yuehao Song, Yujie Xing
SWRouter is a new routing method for multi‑turn large language model conversations that uses a similarity‑based context segmentation mechanism to construct prompts and a dual‑metric evaluation framework to separate construction accuracy from router performance. The approach addresses two key challenges in multi‑turn dialogue: preventing information loss or confusion during context construction and evaluating routing quality independently of prompt quality. Experiments on multi‑turn dialogue benchmarks show that SWRouter outperforms strong baselines, improving evaluation accuracy by 16.26% over the best individual large language model and by 8.22% over the Conv‑ID Context baseline.
By Yu Wang, Yuchen Li, Rui Kong, Xinran Chen, Jiamin Chen, Hengyi Cai, Shuaiqiang Wang, Jiashu Zhao, Yulun Zhang, Zhonghao Lyu, Haoyi Xiong, Linghe Kong, Jimmy Xiangji Huang, Dawei Yin
The paper presents a method for reconstructing 3D wireframes from single 2D line drawings by treating the task as conditional depth estimation. It uses a Latent Diffusion Model with spatial conditioning on the sketch and optional partial-depth cues to predict depth for each drawn pixel, producing a 3D wireframe that faithfully matches the visible strokes. Trained on over three million synthetic image‑depth pairs from CAD wireframes, the approach achieves a best‑of‑five normalized depth error of 3.9% and demonstrates robust performance across varying shape complexities.
By Elton Cao, Hod Lipson
The paper introduces the task alignment proxy, a method that accelerates hyperparameter selection for merging models fine‑tuned on diverse vision tasks. It addresses the challenge of training heterogeneous decoders, which makes traditional downstream performance evaluation costly. By using the proxy, the authors demonstrate that model merging can be applied efficiently to multi‑task vision models beyond CLIP‑based classification.
By Pau de Jorge, C\'esar Roberto de Souza, Bj\"orn Michele, Mert B\"ulent Sar{\i}y{\i}ld{\i}z, Philippe Weinzaepfel, Florent Perronnin, Diane Larlus, Yannis Kalantidis
TailProp introduces a hierarchical vision backbone that uses a Tail Propagation Operator (TPO) combining Gaussian and Cauchy stable-process propagators to adaptively mix rapid and heavy-tailed spatial influences. The operator predicts a content-conditioned, channel-wise coefficient that fuses the two responses in the DCT domain, achieving efficient $O(N^{1.5})$ spatial mixing. Across multiple vision tasks, TailProp consistently outperforms matched propagation baselines, achieving state‑of‑the‑art results on ImageNet, COCO, and ADE20K.
By Jiahao Kong, Zihan Li
SegCol is a new dataset and benchmark for semantic segmentation of colon fold edges and surgical instruments in colonoscopy images, derived from the EndoMapper dataset. It offers manually annotated pixel‑level masks for three instrument classes and thin fold‑edge structures across temporally consistent image sequences, and serves as the basis for the SegCol Challenge within the EndoVis Challenge at MICCAI 2024. The study evaluates supervised segmentation and annotation‑efficient active learning, analyzes various segmentation metrics under structural perturbations, and highlights how metric behavior depends on target structure, underscoring the need for carefully selected evaluation protocols in endoscopic segmentation.
By Xinwei Ju, Rema Daher, Razvan Caramalau, Baoru Huang, Danail Stoyanov, Francisco Vasconcelos
The paper surveys how large language models (LLMs) are being applied in legal tasks such as judgement prediction, document analysis, and drafting. It reviews the benefits of automation while highlighting legal challenges like privacy, bias, and explainability. The authors also discuss data resources for legal domain specialization and outline future research directions.
By Zhongxiang Sun
The paper introduces SSS, a semi‑supervised framework that builds on the Vision Foundation Model SAM‑2 to improve medical image segmentation. It combines a weak‑to‑strong consistency regularization with a Discriminative Feature Enhancement mechanism and a prompt generator that uses Physical Constraints with a Sliding Window to supply prompts for unlabeled data. Experiments on the ACDC and BHSD datasets show that SSS outperforms prior methods, achieving a 53.15 Dice score on BHSD, a +3.65 improvement over the state of the art.
By Hongjie Zhu, Xiwei Liu, Rundong Xue, Zeyu Zhang, Yong Xu, Daji Ergu, Ying Cai, Yang Zhao
Artic-O is an end‑to‑end, feed‑forward framework that reconstructs articulated objects from sparse images by learning latent geometry. It maps multi‑state observations into a pretrained latent geometry space, uses a frozen flow‑matching decoder for complete‑shape priors, and fuses visual tokens with geometry latents in an image‑grounded part‑reasoning module to segment active parts and predict articulation. Trained with a geometry‑to‑articulation curriculum and a decoupled two‑pass strategy, Artic‑O achieves high reconstruction quality and articulation accuracy while drastically reducing inference time from 9 minutes to about 0.3 seconds per object.
By Xuyang Wang, Zhenyu Li, Jian Ding, Habib Slim, Peter Wonka, Hongdong Li, Mohamed Elhoseiny
MC-DeTra is a reimplementation of the DeTra model that jointly performs object detection and socially-aware trajectory forecasting in bird's-eye-view images. It introduces motion-consistency mechanisms that add supervision from each actor’s past motion, surrounding traffic occupancy, and a consistency constraint aligning predicted heading with motion direction. The added losses are train‑only and inference‑safe, improving dynamic trajectory forecasting on the Waymo Open Dataset while maintaining or enhancing detection accuracy.
By Vladislav Diuzhev, Dmitry Yudin
The study compares five pre‑trained convolutional neural networks—ResNet50, VGG16, VGG19, MobileNet, and InceptionV3—for melanoma detection using dermatoscopic and histopathological image datasets. Accuracy varied across models and modalities, with ResNet50 achieving the highest scores (84% on HAM10000 and 83% on CR‑AI4SkIN) and InceptionV3 the lowest (71% on ISIC 2018). The results show that a model’s performance on dermatoscopic images does not necessarily predict its performance on histopathological images.
By Wagner Moreno Schmitz, Marco Antonio de Castro Barbosa, Thiago Magalh\~aes Amaral, Dalcimar Casanova, Jefferson Tales Oliva
SG-Blend introduces a per‑layer adaptive activation that interpolates between a bias‑corrected, parametric Swish variant (SSwish) and GELU, using a learnable blend coefficient, sharpness, and zero‑centering bias. The method adds only three scalars per feed‑forward block and, on BERT‑style IMDB classification, matches peak accuracy while reducing seed‑to‑seed variance by 42 %. It also achieves the lowest validation perplexity on WikiText103 and generalizes to computer vision and other domains.
By Gaurav Sarkar, Syed Affan Daimi, Jay Gala, Subarna Tripathi
The paper explores soft prompting for few‑shot object detection with vision‑language models, showing that optimizing a small number of continuous prompt tokens—especially when placed at the cross‑modal boundary and initialized from an empty space token—can match LoRA performance while training far fewer parameters. Soft prompting also avoids catastrophic forgetting, transfers to newer models, and can be verbalized into readable prompts. The study extends these findings to manipulation tasks, indicating that VLMs already contain much of the necessary knowledge for specialized domains, and the main challenge is learning how to ask for it.
By Gautam Rajendrakumar Gare, Siyi Li, Hewei Wang, Cesar Daniel Hernandez, Wei Zhao, Wolfgang M. Pauli, John Galeotti, Deva Ramanan
The paper evaluates the new YOLO26 architecture, which offers NMS-free end-to-end inference and is tailored for CPU-based edge devices, against three earlier Ultralytics models (YOLOv5u, YOLOv8, and YOLO11) in aquaculture fish mortality detection. Across nano, small, and medium scales, all models achieved similar detection accuracy on a full dataset, but differences emerged in data efficiency and deployment performance: YOLOv8 reached 90% mAP50 with only 400 images, while YOLO26 variants needed 1,000 images; YOLO26n was fastest on a Raspberry Pi 5 (7.51 FPS), whereas YOLOv5mu led on CPU-based hardware. The study concludes that architectural novelty alone does not dictate suitability for edge AI in aquaculture; training data size, target hardware, and inference needs must be jointly considered.
By Rakesh Ranjan, Gajanan S. Kothawade, Kata Sharrer, Scott Tsukuda, Christopher Good
The paper introduces a predictive tracking method for optical coherence tomography (OCT) that propagates positional updates across multiple landmarks to estimate a global 6D pose. By doing so, it achieves robust tracking at higher velocities, reporting root‑mean‑square errors below 1 mm for speeds up to 100 mm/s while tracking up to nine landmarks sequentially.
By Konrad Reuter, Suresh Guttikonda, Chaitali Uday Karekar, Christian Betz, Alexander Schlaefer