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
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 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
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 investigates how to best combine synthetic and real historical Manchu word images for low‑resource OCR. Using 60,000 synthetic and 20,306 real images, the authors compare three pretrained vision‑language models and a compact CRNN across synthetic‑only, real‑only, joint, and sequential training regimes. Adding real data boosts word accuracy to 95–96%, and ensembling the best recognizers raises it to 98.27% without extra training.
FreeFlow is a hierarchical transformer for optical flow estimation that eliminates traditional flow-specific inductive biases such as correlation volumes and feature warping. It relies on a single feed-forward encoder–decoder architecture that incorporates window attention, shifted-window attention, and reduced-resolution global attention. This design allows the model to scale with capacity while achieving state‑of‑the‑art accuracy on Sintel, KITTI‑2015, and Spring benchmarks, all while remaining memory efficient at 1080p inference.
The paper presents a pragmatic segmentation pipeline for brain metastases in the BraTS 2026 Task 1, using a 5‑fold nnU-Net ResEnc‑L ensemble trained for 1,000 epochs on 1,296 four‑modality cases. A rule‑based post‑processing cascade tuned for the lesion‑wise Dice similarity coefficient (LW‑DSC) improves performance, achieving LW‑DSC scores of 0.733, 0.751, 0.713, and 0.549 on enhancing tumour, tumour core, whole tumour, and resection cavity, respectively. The authors audit each post‑processing stage with a five‑fold out‑of‑fold analysis, confirm two stages as robust, and provide a mechanistic analysis of LW‑DSC, along with thirteen negative results that challenge common intuitions.
TailProp introduces a hierarchical vision backbone that adapts propagation dynamics across visual representations using a Tail Propagation Operator (TPO). TPO combines Gaussian and Cauchy stable-process propagators—one with rapidly decaying influence and one with heavy-tailed influence—by predicting a content-conditioned, channel-wise coefficient that fuses the two responses in the DCT domain. The resulting architecture achieves state‑of‑the‑art performance on ImageNet‑1K, Mask R‑CNN, and ADE20K, outperforming matched propagation baselines across multiple vision tasks.
arXiv:2609.10018v1 Announce Type: new
Abstract: EdgeAI systems are increasingly employing computer vision applications to enable intelligent, on-device decision-making in real-time. However, these de...
By Sudaksh Kalra, Dolly Sapra
arXiv:2602.20773v2 Announce Type: replace
Abstract: Purpose: Developing generalizable medical image segmentation models is challenging because imaging data are distributed across institutions and dif...
By Sachin Dudda Nagaraju, Ashkan Moradi, Bendik Skarre Abrahamsen, Mattijs Elschot
arXiv:2507.21816v1 Announce Type: cross
Abstract: Few-shot object detection (FSOD) for optical remote sensing images aims to detect rare objects with only a few annotated bounding boxes. The limited...
By Yanxing Liu, Jiancheng Pan, Bingchen Zhang
arXiv:2609.10322v1 Announce Type: new
Abstract: Transferring the rich priors of large 2D foundation models to sparse 3D LiDAR remains challenging, as training native 3D foundation models at comparabl...
By Samed Do\u{g}an, Nico Leuze, Alfred Sch\"ottl
arXiv:2609.08330v1 Announce Type: new
Abstract: Table detection is a core task in document analysis, supporting downstream applications such as information retrieval, document reconstruction, and vis...
By Dhruv Kudale, Udhay Brahmi, Ganesh Ramakrishnan
arXiv:2605.01234v2 Announce Type: replace
Abstract: We present TT4D, a large-scale, high-fidelity table tennis dataset. It provides $140+$ hours of reconstructed singles and doubles gameplay from mon...
By Nima Rahmanian, Daniel Kienzle, Thomas Gossard, Dvij Kalaria, Rainer Lienhart, Shankar Sastry
arXiv:2609.06898v1 Announce Type: cross
Abstract: Byte Pair Encoding (BPE) constructs vocabularies through greedy pair merging, but the resulting merge order does not necessarily allocate a fixed mod...
By Kenny Shao
arXiv:2509.04757v2 Announce Type: replace-cross
Abstract: Hurricanes cause widespread damage to buildings, roads, and other infrastructure, making timely post-disaster damage assessment critical for...
By Zhangding Liu, Neda Mohammadi, John E. Taylor
arXiv:2609.06959v1 Announce Type: cross
Abstract: 3D point cloud semantic segmentation is essential for real-world spatial understanding, yet the prohibitive cost of human annotations motivates unsup...
By Zhenghao Zhang, Xinjie Wang, Wei Wang, Jun Zhang, Hanyun Wang
The paper introduces Multi-Negative Direct Preference Optimisation (MDPO), a pairwise objective that compares the correct entity with all valid rejected candidates for each mention, extending the single-negative approach used in prior work. MDPO retains the Bradley‑Terry formulation of Direct Preference Optimisation while leveraging the full candidate set through masked, length‑normalised sequence scores. Experiments on French, German, English, Swedish, and Finnish historical newspaper datasets (hipe‑2020 and newseye) show that MDPO outperforms both supervised fine‑tuning and single‑negative DPO, especially for NIL mentions, semantic ambiguity, OCR noise, and historically challenging names, and highlight candidate retrieval as a key bottleneck.
By Tien Nam Nguyen, Emanuela Boros, Ahmed Hamdi, Adam Jatowt, Micka\"el Coustaty, Antoine Doucet
arXiv:2609.05516v1 Announce Type: cross
Abstract: Unified perception enables autonomous driving systems to perform object detection, drivable-area segmentation, and lane segmentation within a single...
By Zhiyuan Nie, Zixi Zhou, Xianbin Gu
arXiv:2609.06245v1 Announce Type: cross
Abstract: Multimodal Large Language Models (MLLMs) perform strongly on general visual understanding tasks such as visual question answering, yet they often str...
By Yixin Wan, Tianle Zheng, Kai-Wei Chang