SPECTRA is a parameter‑efficient fine‑tuning framework for geospatial foundation models that tackles two key challenges: spectral mismatch and high adaptation cost. It introduces Band‑Routed Embedding (BRE) to map downstream sensor bands into the pretrained model’s expected band space, enabling full use of available spectral data without altering the patch embedding interface. Additionally, Stage‑wise Transferability‑aware LoRA (ST‑LoRA) estimates stage‑wise transferability and assigns LoRA ranks accordingly, concentrating trainable parameters on the most transferable stages and reducing overall adaptation cost.
By Xingyan Li, Jordan A. Caraballo-Vega, Jie Gong, Mark L. Carroll, Jianwu Wang
The paper introduces two lightweight spectral adapters—Directional Spectral Adapter (DiSECT) and Spectral Instance-Guided Adapter (SiGA)—to adapt the Segment Anything Model (SAM) for accurate segmentation of colorectal liver metastases in contrast‑enhanced CT scans. SiGA achieves the highest single‑point Dice score of 0.77 and performs comparably to a 3D nnU‑Net baseline under no‑prompt inference, while DiSECT requires only 0.14 million trainable parameters. The study evaluates the adapters on 446 CT volumes across various prompting regimes, demonstrating that spectral adapters can efficiently adapt SAM with limited trainable parameters while maintaining strong segmentation accuracy.
By Ramtin Mojtahedi, Mohammad Hamghalam, Jacob J. Peoples, Natalie Gangai, Mithat Gonen, Yun Shin Chun, HyunSeon Christine Kang, Richard K. G. Do, Amber L. Simpson
The paper introduces a deep‑learning pipeline that improves detection of faint moving objects in optical space situational awareness imagery. It combines a Tiny‑U‑Net segmentation network to mask stars with a partial‑convolution variational autoencoder (astro‑VAE) that learns background statistics and performs context‑aware inpainting. The reconstructed, star‑free backgrounds are used as a preprocessing step before detection, and when integrated with a shift‑and‑stack scheme, the method shows high‑fidelity background reconstruction and significant enhancement of moving‑target detectability in real ground‑based telescope data.
By Angela Cratere, Luca Ghilardi, Vishnu Reddy, Francesco Dell'Olio, Charalampos S. Kouzinopoulos, Roberto Furfaro
The paper introduces CalSAM, a lightweight adaptation framework that fine‑tunes only the mask decoder of the Segment Anything Model (SAM) while keeping its encoders frozen. CalSAM employs a Feature Fisher Information Penalty (FIP) to reduce encoder sensitivity to domain shift and a Confidence Misalignment Penalty (CMP) to curb overconfident voxel‑wise errors. Experiments on cross‑center, scanner‑shift, and motion‑corrupted brain MRI datasets show significant gains in Dice similarity coefficient, Hausdorff distance, and expected calibration error, with only a modest training‑time overhead.
By Behraj Khan, Tahir Qasim Syed, Syed Ahmad Chan Bukhari
TextAlign is a post‑training preference‑alignment framework that improves text rendering in large text‑to‑image generative models without changing the generator architecture. It uses a hierarchical vision‑language model to reward global, word, and glyph‑level accuracy, converting binary defect judgments into a scalar preference signal that can be optimized with GRPO or DPO. Experiments on FLUX.1‑dev and Z‑Image‑Turbo demonstrate higher OCR‑based text accuracy while preserving overall generation quality, outperforming several foundation and text‑rendering baselines.
By Mingxuan Cui, Jingpu Yang, Fengxian Ji, Qian Jiang, Zhecheng Shi, Jiaming Wang, Zirui Song, Zhuohan Xie, Fajri Koto, Xiuying Chen
The paper introduces a densely labeled coastal dataset of over 1,000 images from Oahu, Hawaii, featuring 18 semantic classes and 7,400 annotated instances. Seven modern vision‑language models were evaluated using text‑to‑mask, mask‑to‑mask, and mask‑to‑text alignment experiments. Results show that broad landscape classes are recognized more accurately than conventional object and coastal classes, with coastal concepts posing the greatest challenge; however, performance differences are not solely due to environmental context, and alternative textual labels improve recognition of several coastal concepts.
By Seth Knoop, Chad R. Samuelson, Gabriel R. Slade, Brady Moon, Joshua G. Mangelson
UBone3D is a new framework that completes 3D anatomical shapes from partial ultrasound point clouds using physics-rectified conditional flow matching. It models ultrasound artifacts with a simulated physics proxy and applies test-time physics rectification to guide the completion. The method combines a CT-trained generative shape prior and a physics consistency network, achieving higher reconstruction accuracy and anatomical fidelity than existing baselines.
By Weiying Chen, Yuchong Gao, Siyuan Li, Marek Reformat, Rui Zheng, Edmond Lou
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
The paper introduces Sewer-Transformer-ML, a hierarchical vision Transformer that fuses multi‑level features for multi‑label sewer defect classification, and two lightweight variants, Sewer-MobileNet-ML and Sewer-Mobile-TransNet, tailored for resource‑constrained inspection scenarios. On the Sewer‑ML test set, Sewer‑Transformer‑ML‑Base achieved an $F2_{ ext{CIW}}$ of 65.68% and an $F1_{ ext{Normal}}$ of 92.68%, topping the public leaderboard and surpassing the next best method by 7.6 percentage points in $F2_{ ext{CIW}}$. The lightweight Sewer‑MobileNet‑ML reached a comparable $F2_{ ext{CIW}}$ of 65.73% with only 17 M parameters, a 95% reduction from the base model, while Sewer‑Mobile‑TransNet achieved 96.43% accuracy under the standard data split, and ablation studies highlighted the effectiveness of direct concatenation for Transformer features and attention‑based fusion for multiscale CNN features.
By Xu Fang, Zhuoran Wang, Qing Li, Shengyu Zhang, Guanzhi Deng, Jianbiao He, Qingquan Li
The paper introduces two YOLOv11-based instance segmentation models that simultaneously perform wound boundary segmentation and wound classification across five clinically relevant wound types. Using a balanced dataset of 2,963 annotated images and data augmentation, the models achieve high performance, with YOLOv11x excelling in boundary segmentation and YOLOv11m and YOLOv11l leading in classification metrics. The lightweight YOLOv11n variant offers comparable accuracy with lower computational demands, making it suitable for resource-constrained clinical and remote care deployments.
By Mehedi Hasan Tusar, Fateme Fayyazbakhsh, Igor Melnychuk, Ming C. Leu
SegKAN is a new model for high‑resolution medical image segmentation that tackles fragmentation and noise in hepatic vessel CT scans. It replaces the standard embedding module with a novel convolutional network to smooth noise and avoid gradient explosion, and reinterprets spatial relationships between Patch blocks as temporal relationships to better capture positional dependencies. Experiments on a hepatic vessel dataset show a 1.78% improvement in Dice score over the current state‑of‑the‑art model, indicating that the new structure enhances segmentation performance for extended objects.
By Shengbo Tan, Rundong Xue, Shipeng Luo, Zeyu Zhang, Xinran Wang, Lei Zhang, Daji Ergu, Zhang Yi, Yang Zhao, Ying Cai
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
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
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 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
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
The paper presents a few-shot regression framework for plant growth estimation that combines Vision Transformer embeddings, fuzzy c-means clustering for task construction, and gradient-based meta-learning. It demonstrates that structuring tasks in the embedding space is crucial for performance and that second-order meta-learning methods such as MAML++ outperform classical baselines in low-label scenarios. Experiments on two plant datasets confirm that this approach yields reliable growth estimates even with severe label scarcity.
By Sheikh Hasan Elahi, Rusith Chamara Hathurusinghe Dewage, Habib Ullah, Muhammad Salman Siddiqui, Rakibul Islam, Fadi Al Machot
arXiv:2609. 09404v1 Announce Type: cross Abstract: Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services.
By Viet K. Nguyen, Mohammad I. Husain
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
FreeFlow is a hierarchical transformer for optical flow estimation that eliminates traditional flow-specific inductive biases such as correlation volumes, feature warping, and iterative refinement. It relies on a single feed-forward encoder–decoder architecture that integrates window attention for local processing, shifted-window attention for cross-window communication, and global attention at reduced resolution. This design allows the model to scale naturally with capacity, achieving state-of-the-art performance on Sintel, KITTI-2015, and Spring benchmarks while remaining memory efficient at 1080p inference.
By Vladislav Bargatin, Alexander Yakovenko, Khaled Abud, Dmitriy Vatolin