Alexey A. Shvets

Mikhail L. Arbuzov, Sisong Bei, Ziwei Dong et al.

We introduce Telegraph English (TE), a prompt-compression protocol that rewrites natural language into a symbol-rich, formally-structured dialect. Where token-deletion methods such as LLMLingua-2 train a classifier to delete low-importance tokens at a fixed ratio, TE performs a full semantic rewrite: it decomposes the input into atomic fact lines, substitutes verbose phrases with $\sim$40 logical and relational symbols, and lets the compression ratio adapt to each document's information density. A consequence of the line-structure rule is that compression and semantic chunking become the same operation -- each output line is an independently addressable fact, so the compressed representation is simultaneously a semantic index. We evaluate TE on 4{,}081 question-answer pairs from LongBench-v2 across five OpenAI models and two difficulty levels. At roughly 50\% token reduction, TE preserves 99.1\% accuracy on key facts with GPT-4.1 and outperforms LLMLingua-2 at matched compression ratios on every model and task tested. The gap widens on smaller models -- up to 11 percentage points on fine-detail tasks -- suggesting that explicit relational structure compensates for limited model capacity. We release the grammar specification, compression prompt, benchmark data, and reference implementation.

Karthik Raghu Iyer, Yazdan Jamshidi, Nicholas Bray et al.

We introduce a reusable framework for auditing whether LLM attack benchmarks collectively cover the threat surface: a 4$\times$6 Target $\times$ Technique matrix grounded in STRIDE, constructed from a 507-leaf taxonomy -- 401 data-populated and 106 threat-model-derived leaves -- of inference-time attacks extracted from 932 arXiv security studies (2023--2026). The matrix enables benchmark-external validation -- auditing collective coverage rather than individual benchmark consistency. Applying it to six public benchmarks reveals that the three primary frameworks (HarmBench, InjecAgent, AgentDojo) occupy non-overlapping cells covering at most 25\% of the matrix, while entire STRIDE threat categories (Service Disruption, Model Internals) lack any standardized evaluation, despite published attacks in these categories achieving 46$\times$ token amplification and 96\% attack success rates through mechanisms which no benchmark tests. The corpus of 2,521 unique attack groups further reveals pervasive naming fragmentation (up to 29 surface forms for a single attack) and heavy concentration in Safety \& Alignment Bypass, structural properties invisible at smaller scale. The taxonomy, attack records, and coverage mappings are released as extensible artifacts; as new benchmarks emerge, they can be mapped onto the same matrix, enabling the community to track whether evaluation gaps are closing.

Vladimir I. Iglovikov, Selim Seferbekov, Alexander V. Buslaev et al.

The most common approaches to instance segmentation are complex and use two-stage networks with object proposals, conditional random-fields, template matching or recurrent neural networks. In this work we present TernausNetV2 - a simple fully convolutional network that allows extracting objects from a high-resolution satellite imagery on an instance level. The network has popular encoder-decoder type of architecture with skip connections but has a few essential modifications that allows using for semantic as well as for instance segmentation tasks. This approach is universal and allows to extend any network that has been successfully applied for semantic segmentation to perform instance segmentation task. In addition, we generalize network encoder that was pre-trained for RGB images to use additional input channels. It makes possible to use transfer learning from visual to a wider spectral range. For DeepGlobe-CVPR 2018 building detection sub-challenge, based on public leaderboard score, our approach shows superior performance in comparison to other methods. The source code corresponding pre-trained weights are publicly available at https://github.com/ternaus/TernausNetV2

Alexey Shvets, Vladimir Iglovikov, Alexander Rakhlin et al.

Accurate detection and localization for angiodysplasia lesions is an important problem in early stage diagnostics of gastrointestinal bleeding and anemia. Gold-standard for angiodysplasia detection and localization is performed using wireless capsule endoscopy. This pill-like device is able to produce thousand of high enough resolution images during one passage through gastrointestinal tract. In this paper we present our winning solution for MICCAI 2017 Endoscopic Vision SubChallenge: Angiodysplasia Detection and Localization its further improvements over the state-of-the-art results using several novel deep neural network architectures. It address the binary segmentation problem, where every pixel in an image is labeled as an angiodysplasia lesions or background. Then, we analyze connected component of each predicted mask. Based on the analysis we developed a classifier that predict angiodysplasia lesions (binary variable) and a detector for their localization (center of a component). In this setting, our approach outperforms other methods in every task subcategory for angiodysplasia detection and localization thereby providing state-of-the-art results for these problems. The source code for our solution is made publicly available at https://github.com/ternaus/angiodysplasia-segmentatio

Alexey Shvets, Alexander Rakhlin, Alexandr A. Kalinin et al.

Semantic segmentation of robotic instruments is an important problem for the robot-assisted surgery. One of the main challenges is to correctly detect an instrument's position for the tracking and pose estimation in the vicinity of surgical scenes. Accurate pixel-wise instrument segmentation is needed to address this challenge. In this paper we describe our winning solution for MICCAI 2017 Endoscopic Vision SubChallenge: Robotic Instrument Segmentation. Our approach demonstrates an improvement over the state-of-the-art results using several novel deep neural network architectures. It addressed the binary segmentation problem, where every pixel in an image is labeled as an instrument or background from the surgery video feed. In addition, we solve a multi-class segmentation problem, where we distinguish different instruments or different parts of an instrument from the background. In this setting, our approach outperforms other methods in every task subcategory for automatic instrument segmentation thereby providing state-of-the-art solution for this problem. The source code for our solution is made publicly available at https://github.com/ternaus/robot-surgery-segmentation

Vladimir Iglovikov, Alexey Shvets

Pixel-wise image segmentation is demanding task in computer vision. Classical U-Net architectures composed of encoders and decoders are very popular for segmentation of medical images, satellite images etc. Typically, neural network initialized with weights from a network pre-trained on a large data set like ImageNet shows better performance than those trained from scratch on a small dataset. In some practical applications, particularly in medicine and traffic safety, the accuracy of the models is of utmost importance. In this paper, we demonstrate how the U-Net type architecture can be improved by the use of the pre-trained encoder. Our code and corresponding pre-trained weights are publicly available at https://github.com/ternaus/TernausNet. We compare three weight initialization schemes: LeCun uniform, the encoder with weights from VGG11 and full network trained on the Carvana dataset. This network architecture was a part of the winning solution (1st out of 735) in the Kaggle: Carvana Image Masking Challenge.

Mikhail L. Arbuzov, Alexey A. Shvets, Sisong Beir

The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-token error probabilities, posits an inherent limitation for long autoregressive outputs. Our research fundamentally challenges this view by synthesizing emerging evidence that LLM errors are not uniformly distributed but are concentrated at sparse "key tokens" ($5-10\%$ of total tokens) representing critical decision junctions. By distinguishing these high-impact tokens from the increasingly predictable majority, we introduce a new reliability formula explaining the sustained coherence of modern LLMs over thousands of tokens. Converging research streams reveal that long-context performance primarily depends on accurately navigating a few crucial semantic decision points rather than on uniform token-level accuracy, enabling targeted strategies that significantly outperform brute-force approaches. We thus propose a framework for next-generation systems centered on selective preservation of semantically vital tokens, dynamic computational allocation at uncertain decision boundaries, multi-path exploration at ambiguities, and architectures aligned with natural semantic domains. This marks a fundamental shift from raw scaling to strategic reasoning, promising breakthrough performance without proportionate computational scaling and offering a more nuanced understanding that supersedes the exponential decay hypothesis, thereby opening pathways toward substantially more powerful and efficient language systems.

Alexander Rakhlin, Aleksei Tiulpin, Alexey A. Shvets et al.

Breast cancer is one of the main causes of death worldwide. Histopathological cellularity assessment of residual tumors in post-surgical tissues is used to analyze a tumor's response to a therapy. Correct cellularity assessment increases the chances of getting an appropriate treatment and facilitates the patient's survival. In current clinical practice, tumor cellularity is manually estimated by pathologists; this process is tedious and prone to errors or low agreement rates between assessors. In this work, we evaluated three strong novel Deep Learning-based approaches for automatic assessment of tumor cellularity from post-treated breast surgical specimens stained with hematoxylin and eosin. We validated the proposed methods on the BreastPathQ SPIE challenge dataset that consisted of 2395 image patches selected from whole slide images acquired from 64 patients. Compared to expert pathologist scoring, our best performing method yielded the Cohen's kappa coefficient of 0.70 (vs. 0.42 previously known in literature) and the intra-class correlation coefficient of 0.89 (vs. 0.83). Our results suggest that Deep Learning-based methods have a significant potential to alleviate the burden on pathologists, enhance the diagnostic workflow, and, thereby, facilitate better clinical outcomes in breast cancer treatment.

Max Allan, Alex Shvets, Thomas Kurmann et al.

In mainstream computer vision and machine learning, public datasets such as ImageNet, COCO and KITTI have helped drive enormous improvements by enabling researchers to understand the strengths and limitations of different algorithms via performance comparison. However, this type of approach has had limited translation to problems in robotic assisted surgery as this field has never established the same level of common datasets and benchmarking methods. In 2015 a sub-challenge was introduced at the EndoVis workshop where a set of robotic images were provided with automatically generated annotations from robot forward kinematics. However, there were issues with this dataset due to the limited background variation, lack of complex motion and inaccuracies in the annotation. In this work we present the results of the 2017 challenge on robotic instrument segmentation which involved 10 teams participating in binary, parts and type based segmentation of articulated da Vinci robotic instruments.

Alexander V. Buslaev, Selim S. Seferbekov, Vladimir I. Iglovikov et al.

Analysis of high-resolution satellite images has been an important research topic for traffic management, city planning, and road monitoring. One of the problems here is automatic and precise road extraction. From an original image, it is difficult and computationally expensive to extract roads due to presences of other road-like features with straight edges. In this paper, we propose an approach for automatic road extraction based on a fully convolutional neural network of U-net family. This network consists of ResNet-34 pre-trained on ImageNet and decoder adapted from vanilla U-Net. Based on validation results, leaderboard and our own experience this network shows superior results for the DEEPGLOBE - CVPR 2018 road extraction sub-challenge. Moreover, this network uses moderate memory that allows using just one GTX 1080 or 1080ti video cards to perform whole training and makes pretty fast predictions.

Selim S. Seferbekov, Vladimir I. Iglovikov, Alexander V. Buslaev et al.

Semantic segmentation is in-demand in satellite imagery processing. Because of the complex environment, automatic categorization and segmentation of land cover is a challenging problem. Solving it can help to overcome many obstacles in urban planning, environmental engineering or natural landscape monitoring. In this paper, we propose an approach for automatic multi-class land segmentation based on a fully convolutional neural network of feature pyramid network (FPN) family. This network is consisted of pre-trained on ImageNet Resnet50 encoder and neatly developed decoder. Based on validation results, leaderboard score and our own experience this network shows reliable results for the DEEPGLOBE - CVPR 2018 land cover classification sub-challenge. Moreover, this network moderately uses memory that allows using GTX 1080 or 1080 TI video cards to perform whole training and makes pretty fast predictions.