{"total":36,"items":[{"citing_arxiv_id":"2605.22222","ref_index":50,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models","primary_cat":"cs.LG","submitted_at":"2026-05-21T09:26:16+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21017","ref_index":40,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Physics-informed neural networks for quantitative assessment of cancellous bone microstructure from photoacoustic signals","primary_cat":"physics.med-ph","submitted_at":"2026-05-20T10:50:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Biot-PINN embeds Biot poroelasticity into a neural network to decode photoacoustic signals for cancellous bone microstructure grading at 97% accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09639","ref_index":18,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"XTinyU-Net: Training-Free U-Net Scaling via Initialization-Time Sensitivity","primary_cat":"eess.IV","submitted_at":"2026-05-10T16:34:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A Jacobian sensitivity curve computed at initialization identifies the narrowest U-Net configuration that avoids performance collapse, matching nnU-Net accuracy with 400-1600x fewer parameters on six medical datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08856","ref_index":12,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Controlling Transient Amplification Improves Long-horizon Rollouts","primary_cat":"cs.LG","submitted_at":"2026-05-09T10:10:30+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Commutativity regularization mitigates transient error amplification in autoregressive neural simulators by penalizing non-normality and non-commutativity of Jacobians, yielding stable long-horizon rollouts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07167","ref_index":37,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"GPROF-IR: An Improved Single-Channel Infrared Precipitation Retrieval for Merged Satellite Precipitation Products","primary_cat":"physics.ao-ph","submitted_at":"2026-05-08T03:02:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GPROF-IR is a CNN-based retrieval that uses temporal context in geostationary IR observations to produce precipitation estimates with lower error than prior IR methods and climatological consistency with PMW retrievals for integration into IMERG V08.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05683","ref_index":55,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization","primary_cat":"stat.ML","submitted_at":"2026-05-07T05:19:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Spectral analysis of activations and gradients provides new diagnostics that link batch size to representation geometry, early covariance tails to token efficiency, and spectral shifts to learning dynamics in decoder-only LLMs, backed by a mechanistic model.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"anogpt/blob/master/records/track_1_short/2024-11-19_FlexAttention/8384493d-dba 9-4991-b16b-8696953f5e6d.txt. [54] KellerJordan/modded-nanogpt contributors. modded-nanogpt record 13: Attention window warmup, 2024. URL https://github.com/KellerJordan/modded-nanogpt/blob/master/r ecords/track_1_short/2024-11-24_WindowWarmup/cf9e4571-c5fc-4323-abf3-a98d862ec 6c8.txt. [55] KellerJordan/modded-nanogpt contributors. modded-nanogpt record 14: Value embeddings, 2024. URL https://github.com/KellerJordan/modded-nanogpt/tree/master/records/t rack_1_short/2024-12-04_ValueEmbed. [56] KellerJordan/modded-nanogpt contributors. modded-nanogpt record 16: Split value embeddings, block sliding window, separate block mask, 2024. URLhttps://github."},{"citing_arxiv_id":"2605.05488","ref_index":20,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Robust Foundation Model for Conservation Laws: Injecting Context into Flux Neural Operators via Recurrent Vision Transformers","primary_cat":"cs.LG","submitted_at":"2026-05-06T22:23:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A recurrent Vision Transformer hypernetwork injects context into Flux Neural Operators to infer and solve unseen conservation laws while preserving robustness and long-time stability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02737","ref_index":65,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"SIAM: Head and Brain MRI Segmentation from Few High-Quality Templates via Synthetic Training","primary_cat":"cs.CV","submitted_at":"2026-05-04T15:37:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SIAM achieves state-of-the-art whole-head MRI segmentation of 16 structures including extra-cerebral tissues by training on synthetic data from just six manual templates, matching or exceeding prior methods on 301 scans across eight heterogeneous datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.26478","ref_index":16,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Cross-Domain Transfer of Hyperspectral Foundation Models","primary_cat":"cs.CV","submitted_at":"2026-04-29T09:43:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Cross-domain transfer of remote-sensing HSI foundation models improves proximal sensing semantic segmentation over in-domain training and narrows the gap to cross-modality methods on the HS3-Bench benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.25890","ref_index":17,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Observation-Guided Neural Surrogate Learning for Scientific Simulation Emulation: A Single-Gauge Flood-Inundation Proof of Concept","primary_cat":"physics.ao-ph","submitted_at":"2026-04-28T17:33:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An EnsCGP coarse surrogate plus U-Net-ASPP corrector emulates LISFLOOD-FP flood depths on a 256x256 grid around one Chicago gauge, achieving R² ≈ 0.99 and MAE < 0.01 m on held-out events while matching the gauge depth at that single pixel.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24347","ref_index":60,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Semantic Segmentation for Histopathology using Learned Regularization based on Global Proportions","primary_cat":"eess.IV","submitted_at":"2026-04-27T11:42:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VSLP infers dense segmentations from global label proportions via a pre-trained transformer for initial confidence maps followed by variational optimization using Wasserstein fidelity and a learned regularizer, outperforming prior weakly supervised methods on histopathology datasets.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"Training in the first stage required approximately 16 hours, while the second stage required approximately 50 hours on a single NVIDIA A40 GPU. 4.2 Comparison with State-of-the-Art Methods The segmentation performance of our method was compared with recent MIL methods (SA-MIL [33], WSSS-T [32], DS Type Method Dice↑mIoU↑95HD↓RINGS dataset Unsup. MedSAM [60] 0.656±0.21 0.524±0.23 418±316 MIL LPLP [39] 0.587±0.24 0.398±0.19 321±262 SA-MIL [33] 0.785±0.19 0.678±0.2 271±268 WSSS-T [32] 0.789±0.19 0.674±0.19 286±260 C2C [30] 0.781±0.19 0.671±0.21 251±251 PistoSeg [8] 0.798±0.19 0.682±0.2 278±273 OEEM [7] 0.791±0.23 0.679±0.23 313±287 URN [11]0.867±0.10 0.783±0.15 115±98 LLP SA-MIL [33] 0.42±0.2 0.243±0.17 403±299"},{"citing_arxiv_id":"2604.22506","ref_index":52,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"ICPR 2026 Competition on Low-Resolution License Plate Recognition","primary_cat":"cs.CV","submitted_at":"2026-04-24T12:36:09+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The ICPR 2026 LRLPR competition on real low-quality license plate images drew 99 valid submissions, with the winning team reaching 82.13% recognition rate and four teams exceeding 80%.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"4th PlaceThe fourth-place team (Capture And Predict Plate - CAP2), from Handong Global University (Republic of Korea), proposed a multi-stage pipeline combining geometry-aware preprocessing, dual-stream recognition, and position- wise ensemble, as illustrated in Fig. 8. The preprocessing stage extends MF- LPR2 [42] with padding, resizing, filtering, and background suppression via U- Net [52]-generated text-region masks. A key modification relative to the orig- inal MF-LPR2 is that, instead of fusing five frames into a single restored im- age (5→1), each frame is treated as an independent restored candidate (5→5). Recognition combined multiple feature extractors (ConvNeXtV2 [65], DI- NOv2 [49], DINOv3 [57]) and recognizers (DETR-Lite [4], DCNv2 [70]) at the"},{"citing_arxiv_id":"2604.20936","ref_index":62,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe","primary_cat":"cs.MM","submitted_at":"2026-04-22T13:11:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AttentionBender applies 2D transforms to cross-attention maps in video diffusion transformers, producing distributed distortions and glitch aesthetics that reveal entangled attention mechanisms while serving as both an XAI probe and creative tool.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Networks for Biomedical Image Segmentation. InMedical Image Computing and Computer-Assisted Intervention - MICCAI 2015, Nassir Navab, Joachim Horneg- ger, William M. Wells, and Alejandro F. Frangi (Eds.). Springer International Publishing, Cham, 234-241. doi:10.1007/978-3-319-24574-4_28 [61] Runway. 2025. Runway Research | Introducing Runway Gen-4.5. [62] Johannes Schneider. 2024. Explainable Generative AI (GenXAI): A Survey, Con- ceptualization, and Research Agenda.Artificial Intelligence Review57, 11 (Sept. 2024), 289. doi:10.1007/s10462-024-10916-x [63] Renee Shelby, Shalaleh Rismani, and Negar Rostamzadeh. 2024. Generative AI in Creative Practice: ML-Artist Folk Theories of T2I Use, Harm, and Harm-"},{"citing_arxiv_id":"2604.20222","ref_index":91,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Localized Tornado Outbreak at the Upstream of a Tropical Easterly Wave in Camarines Norte, Philippines (13 September 2025)","primary_cat":"physics.ao-ph","submitted_at":"2026-04-22T06:10:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A tornado outbreak with simultaneous tornadic supercells occurred in the Philippines within an easterly severe weather regime, documented as the first known instance there.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20213","ref_index":4,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Weighted Knowledge Distillation for Semi-Supervised Segmentation of Maxillary Sinus in Panoramic X-ray Images","primary_cat":"cs.CV","submitted_at":"2026-04-22T06:00:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A semi-supervised framework using weighted knowledge distillation and SinusCycle-GAN refinement achieves 96.35% Dice score for maxillary sinus segmentation in panoramic X-rays from 2,511 patients.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18953","ref_index":4,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"FlowForge: A Staged Local Rollout Engine for Flow-Field Prediction","primary_cat":"cs.LG","submitted_at":"2026-04-21T01:04:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FlowForge predicts flow fields via staged local updates with a shared lightweight predictor, matching or exceeding baselines in accuracy while improving robustness to noise and reducing latency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17575","ref_index":39,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"$\\mu$-FlowNet: A Deep Learning Approach for Mapping Flow Fields in Irregular Microchannels Using an Attention-based U-Net Encoder-Decoder Architecture","primary_cat":"cs.CE","submitted_at":"2026-04-19T18:41:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"μ-FlowNet applies an attention U-Net to map flow fields in irregular microchannels, reporting dice score 0.9317 and IoU 0.8731 on test data while outperforming standard U-Net and T-Net.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"align with the fundamental principles of physics. In this study, we utilize Deep Neural Network (DNN) models especially U-Net archite ctures to develop a mapping between random -shaped geometry and its corresponding fluid flow patterns in terms of velocity components [36]. Although there are few works on image -to-image processing tasks, such as image segmentation [37], [38], [39], [40] but previous studies primarily concentrate on medical or natural images derived from unidentified physical phenomena. These methods lac k the integration of physical concepts to direct neural network training. In our work, the flow prediction challenge is distinct from ordinary image-to-image translations. This is because the flow data we use"},{"citing_arxiv_id":"2604.16955","ref_index":20,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Training-inference input alignment outweighs framework choice in longitudinal retinal image prediction","primary_cat":"cs.CV","submitted_at":"2026-04-18T10:28:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Training-inference input alignment outweighs framework choice for longitudinal retinal image prediction, with deterministic regression matching complex models when acquisition variability dominates disease progression.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"TRU learns a mapping 𝑓𝜃(𝐼𝑁, ℋ, 𝛥𝑡∗) → 𝐼̂∗ that predicts the future retinal image from the most recent observation and the full available history. The architecture and hyperparameters are identical across imaging modalities (FAF and SLO) and across all evaluation cohorts. 3.2 Temporal Conditioning Architecture TRU is built on a multiscale temporal U-Net backbone [20] with approximately 22.8M parameters. The architecture integrates two core design elements: continuous time-delta conditioning encoding the temporal distance from each history frame to the prediction target, and multi-scale history feature extraction with delta-weighted aggregation. The backbone is a four- level encoder-decoder with channel widths (64, 128, 256, 512) and skip connections at all scales"},{"citing_arxiv_id":"2604.15964","ref_index":28,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Topology-Driven Fusion of nnU-Net and MedNeXt for Accurate Brain Tumor Segmentation on Sub-Saharan Africa Dataset","primary_cat":"eess.IV","submitted_at":"2026-04-17T11:29:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Pre-training nnU-Net and MedNeXt on BraTS 2025 data then fine-tuning on BraTS-Africa with added topology refinement yields NSD scores of 0.810, 0.829, and 0.895 for SNFH, NETC, and ET.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10702","ref_index":32,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Architecture-Agnostic Modality-Isolated Gated Fusion for Robust Multi-Modal Prostate MRI Segmentation","primary_cat":"cs.CV","submitted_at":"2026-04-12T15:54:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MIGF improves multi-modal prostate MRI segmentation robustness via modality-isolated streams and dropout training, yielding ranking score gains of 2.8-13.4% across backbones and better tolerance to degraded diffusion sequences on PI-CAI and Prostate158.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08781","ref_index":17,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"PSIRNet: Deep Learning-based Free-breathing Rapid Acquisition Late Enhancement Imaging","primary_cat":"eess.IV","submitted_at":"2026-04-09T21:31:48+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PSIRNet produces diagnostic-quality free-breathing PSIR LGE cardiac MRI from a single interleaved IR/PD acquisition over two heartbeats using a physics-guided deep learning network trained on over 800,000 slices.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08015","ref_index":2,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Component-Adaptive and Lesion-Level Supervision for Improved Small Structure Segmentation in Brain MRI","primary_cat":"cs.CV","submitted_at":"2026-04-09T09:15:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CATMIL augments nnU-Net with component-adaptive Tversky and MIL-based lesion supervision to raise Dice scores, small-lesion recall, and error control on the MSLesSeg dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.05594","ref_index":20,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"RABC-Net: Reliability-Aware Annotation-Free Skin Lesion Segmentation for Low-Resource Dermoscopy","primary_cat":"cs.CV","submitted_at":"2026-04-07T08:43:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RABC-Net achieves 86.58% DICE and 79.47% JAC on skin lesion segmentation across ISIC-2017, ISIC-2018, and PH2 using only pseudo-labels and no manual masks for training or adaptation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.24985","ref_index":25,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Few-Shot Left Atrial Wall Segmentation in 3D LGE MRI via Meta-Learning","primary_cat":"cs.CV","submitted_at":"2026-03-26T03:25:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"MAML with auxiliary cavity tasks and boundary loss improves 5-shot LA wall segmentation over standard fine-tuning (DSC 0.54 vs 0.48) and nears fully supervised performance at 20 shots.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.13708","ref_index":19,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"RSEdit: Text-Guided Image Editing for Remote Sensing","primary_cat":"cs.CV","submitted_at":"2026-03-14T02:22:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RSEdit adapts off-the-shelf text-to-image models into a collection of editing systems that follow text instructions while keeping geospatial structure intact in remote sensing images.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.02087","ref_index":15,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Detection-Gated Pipeline for Robust Glottal Area Waveform Extraction and Clinical Pathology Assessment","primary_cat":"cs.CV","submitted_at":"2026-03-02T17:05:41+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A detection-gated YOLOv8n-U-Net pipeline extracts glottal area waveforms from high-speed endoscopy videos, achieving cross-dataset DSC of 0.745 and using area coefficient of variation to distinguish healthy from pathological cases in a 40-subject study.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.17205","ref_index":99,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising","primary_cat":"astro-ph.IM","submitted_at":"2026-02-19T09:51:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ASTERIS, a self-supervised spatiotemporal denoising algorithm, improves astronomical detection limits by 1 magnitude at 90% completeness while identifying three times more redshift >9 galaxy candidates in JWST images.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.07859","ref_index":39,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Differentiable Surrogate for Detector Simulation and Design with Diffusion Models","primary_cat":"physics.ins-det","submitted_at":"2026-01-09T17:53:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A LoRA-adapted conditional diffusion surrogate for electromagnetic calorimeter showers matches key observables within 2% RMSE and reproduces directional trends in design-utility gradients.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.04024","ref_index":34,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Predicting parameters of a model cuprate superconductor using machine learning","primary_cat":"physics.comp-ph","submitted_at":"2025-12-03T18:02:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"An adapted U-Net model trained on mean-field phase diagrams accurately predicts Hamiltonian parameters for a cuprate superconductor when validated on Monte Carlo simulation data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.04334","ref_index":10,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Submanifold Sparse Convolutional Networks for Automated 3D Segmentation of Kidneys and Kidney Tumours in Computed Tomography","primary_cat":"cs.CV","submitted_at":"2025-11-06T13:17:16+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A two-stage sparse convolutional network pipeline for native high-resolution 3D kidney and tumor segmentation in CT that matches top Dice scores while reducing VRAM and runtime versus nnU-Net and SegVol.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.24517","ref_index":39,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Physics Priors Offer Useful Accuracy-Carbon Trade-Offs in Spatio-Temporal Forecasting","primary_cat":"cs.LG","submitted_at":"2025-09-29T09:34:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Stronger physics priors in neural networks for spatio-temporal shear flow forecasting yield substantially lower training carbon footprints than weak or no priors, though inference savings are less consistent.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.15753","ref_index":47,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Algebraic Language Models for Inverse Design of Metamaterials via Diffusion Transformers","primary_cat":"cs.CE","submitted_at":"2025-07-21T16:09:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DiffuMeta uses diffusion transformers and algebraic language representations to generate diverse 3D shell metamaterials with targeted stress-strain responses under large deformations including buckling and contact.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2411.09553","ref_index":48,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"OOD-SEG: Exploiting out-of-distribution detection techniques for learning image segmentation from sparse multi-class positive-only annotations","primary_cat":"cs.CV","submitted_at":"2024-11-14T16:06:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"OOD-SEG reframes multi-class segmentation from sparse positive-only annotations as pixel-wise positive-unlabelled learning solved by integrating out-of-distribution detection techniques, with a proposed cross-validation evaluation on surgical imaging datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2406.12632","ref_index":62,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Cyclic 2.5D Perceptual Loss for Cross-Modal 3D Medical Image Synthesis: T1w MRI to Tau PET","primary_cat":"eess.IV","submitted_at":"2024-06-18T13:59:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Proposes a cyclic 2.5D perceptual loss with manufacturer SUVR standardization for T1w MRI to tau PET synthesis, reporting improved regional agreement on ADNI and SCAN cohorts across U-Net, UNETR, SwinUNETR, CycleGAN, and Pix2Pix.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2403.03206","ref_index":172,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","primary_cat":"cs.CV","submitted_at":"2024-03-05T18:45:39+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Biased noise sampling for rectified flows combined with a bidirectional text-image transformer architecture yields state-of-the-art high-resolution text-to-image results that scale predictably with model size.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.09745","ref_index":15,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Respiratory Motion Correction in Abdominal MRI using a Densely Connected U-Net with GAN-guided Training","primary_cat":"eess.IV","submitted_at":"2019-06-24T06:54:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Densely connected U-Net with GAN-guided training and perceptual loss corrects respiratory motion artifacts in abdominal MRI.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}