IntroductionColorectal cancer originates in most cases from polyps that progressively become malignant over time and colonoscopy offers a highly studied early diagnostic strategy to ensure a timely treatment plan. Automatic image segmentation of polyps, using intelligent supervised approaches, achieved good performance, but the need of their large annotated datasets limits the clinical applicability.MethodsThis study presents […]
Controllable Quantum Memory Capacity in Quantum Reservoir Networks with Tunable partial-SWAPs
arXiv:2605.12713v1 Announce Type: cross Abstract: In the field of quantum reservoir computing (QRC), many different computational models and architectures have been proposed. From these models, we identify feedback based models — which use a feedback mechanism to re-embed classical measurements from the QRC — and recurrent models — which use a multi-register approach with memory […]
X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challenge
arXiv:2605.13258v1 Announce Type: cross Abstract: In this work, we present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions. Our method is built upon the strong baseline framework X-Restormer, which effectively captures both channel-wise global dependencies and spatially-local structural information through its dual-attention design (Multi-DConv Head Transposed […]
CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation
arXiv:2605.12938v1 Announce Type: cross Abstract: Camera-conditioned video generation requires positional encoding that remains reliable under changes in camera motion, lens configuration, and scene structure. However, existing attention-level camera encodings either provide ray-only camera signals or rely on pinhole camera geometry, limiting their applicability to general camera control under the Unified Camera Model, including wide-angle and […]
Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency
arXiv:2605.13047v1 Announce Type: cross Abstract: Evaluating whether large vision-language models (VLMs) align with human perception for high-level semantic scene comprehension remains a challenge. Traditional white-box interpretability methods are inapplicable to closed-source architectures and passive metrics fail to isolate causal features. We introduce Counterfactual Semantic Saliency (CSS). This black-box, model-agnostic framework quantifies the importance of objects […]
GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
arXiv:2605.12827v1 Announce Type: cross Abstract: Graph neural networks (GNNs) deployed as cloud services can be emphstolen through emphmodel-extraction attacks, which train a surrogate from query responses to reproduce the target’s behaviour, and a growing line of ownership defenses tries to prevent or trace such theft. The title of this paper asks two questions: emphhow hard […]
Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
arXiv:2605.12748v1 Announce Type: cross Abstract: Large language models (LLMs) can fluently generate student-like responses, making them attractive as simulated students for training and evaluating AI tutors and human educators. Yet such simulators are typically evaluated by output similarity to real students, not by whether they behave like students with coherent misconceptions during interaction. We introduce […]
Discrete MeanFlow: One-Step Generation via Conditional Transition Kernels
arXiv:2605.12805v1 Announce Type: cross Abstract: MeanFlow enables one-step generation in continuous spaces by learning an average velocity over a time interval rather than the instantaneous velocity field of flow matching. However, discrete state spaces do not have smooth trajectories or spatial derivatives, so the continuous formulation does not directly apply. We introduce Discrete MeanFlow, which […]
Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis
arXiv:2605.12869v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary success/failure metrics, failing to capture the temporal dynamics of how attacks succeed under persistent adversarial pressure. This preliminary work […]
Protocol-Driven Development: Governing Generated Software Through Invariants and Evidence
arXiv:2605.12981v1 Announce Type: cross Abstract: Automated program synthesis has reduced the cost of producing candidate implementations, but it introduces a harder governance problem: determining which generated artifacts are admissible in a software system. Natural-language specifications remain semantically ambiguous, and example-based tests sample only part of the behavioral space. Used alone, neither provides a sufficient control […]
N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation
arXiv:2605.13190v1 Announce Type: cross Abstract: Improving the inference efficiency of autoregressive transformers typically means reducing FLOPs per token, usually through approximations that degrade model quality. We introduce N-vium, a mixture-of-exits transformer that partially parallelizes computation across depth on standard hardware, increasing effective FLOPs per second rather than minimizing compute per token. N-vium attaches prediction heads […]
Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety
arXiv:2605.12729v1 Announce Type: cross Abstract: Large language models are increasingly being used to support network operations (NetOps) and artificial intelligence for IT operations (AIOps), including incident investigation, root-cause analysis, configuration synthesis, and limited self-healing. In both NetOps and AIOps, this shift is changing how tasks are managed. Agent-based operations work as workflows, from gathering evidence […]