{"total":11,"items":[{"citing_arxiv_id":"2605.22361","ref_index":38,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Propagation-Consistent Wireless Environment Digital Twin Construction Under Sparse Measurements","primary_cat":"eess.SP","submitted_at":"2026-05-21T11:55:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A method to construct propagation-consistent wireless environment digital twins from sparse CSI by creating a geometry-prior Bayesian channel map and calibrating a scene-level EM property field via differentiable ray tracing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22856","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PilotWiMAE: Pilot-Native Representation Learning for Wireless Channels","primary_cat":"eess.SP","submitted_at":"2026-05-19T06:21:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PilotWiMAE pretrains an encoder on noisy pilots with factorized attention, 99% masking, patch-normalized reconstruction, scale loss, and AWGN curriculum to outperform supervised baselines in cross-frequency beam selection and channel tasks from 3.5 GHz pretraining to 28 GHz evaluation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11828","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PointNeRT: A Physics Aware Neural Ray Tracing Surrogate for Propagation Channel Modeling","primary_cat":"eess.SP","submitted_at":"2026-05-12T09:16:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PointNeRT is a neural surrogate for ray tracing that ingests point clouds and sequentially predicts multipath propagation and attenuation under physics constraints.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"and received fieldE in 0 (p0)has the following form Ein B+1(pB+1) =D B+1FB · · ·D1F0Ein 0 (p0) \u0001 .(9) According to (8), above expression can be rewritten as Ein B+1(pB+1) =I B+1IB · · ·I1 Ein 0 (p0)(10) =T(G(θ, ϕ))e −j2πf τ .(11) whereτ= (λf) −1P b db is total propagation delay, withd b = ∥pb −p b−1∥. The detailed derivation of above formulation can be found in [29]. In PointNeRT model, attenuationIand propagation direction at each interaction point are explicitly predicted, from which the path parameters, such asa l and (θl, ϕl), are obtained. 3 C. Propagation Mechanisms In our work, propagation mechanisms are divided into deter- ministic and non-deterministic interactions based on whether incident and outgoing directions of rays are strictly constrained"},{"citing_arxiv_id":"2605.08772","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fidelity Where it Matters: Site-Specific Nonuniform Refinement for Wireless Digital Twins","primary_cat":"eess.SP","submitted_at":"2026-05-09T07:58:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"An ellipsoid-guided selective refinement algorithm improves radio-map fidelity in urban wireless digital twins by prioritizing refinement of a small subset of buildings using only low-fidelity models.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"vironmentE ⋆, bPdenotes the adopted wireless propagation model, including the considered propagation mechanisms such as line-of-sight (LoS), reflection, diffraction, scattering, and penetration, andθcollects the numerical configurations of the propagation solver. For example, bPcan be instantiated using the existing ray-tracing tools such as NVIDIA Sionna RT [33] and Remcom Wireless InSite [16], whileθmay include the maximum interaction depth, sampling density, and other solver-related parameters. The above WDT model is a structured digital representation of multiple environmental objects, propagation models, and solver configurations, which means that each of these elements can be constructed with different levels of fidelity."},{"citing_arxiv_id":"2605.07781","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Differentiable Ray Tracing with Gaussians for Unified Radio Propagation Simulation and View Synthesis","primary_cat":"cs.CV","submitted_at":"2026-05-08T14:19:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Embedding Gaussian primitives into a ray tracing structure enables unified radio propagation simulation and view synthesis from visual-only reconstructions.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"where λ is the wavelength and Gtx and Grx are the antenna patterns of TX and RX, respectively. Both patterns are functions of the azimuth ϕ and elevation θ angles, with output in C2×1. The symbol Ti denotes the transfer matrix that contains the effect of all EM interactions of the ith path, including free-space path loss. In the case of a specular reflection, the transfer matrix of that kth interaction is defined as [8] Tr k = \u0014 r⊥ 0 0r ∥ \u0015\u0014 e⊤ peku e⊤ pekv e⊤ paku e⊤ pakv \u0015 ,e pe = k×n ||k×n|| 2 ,e pa =e pe ×k, where r⊥ and r∥ are the perpendicular and parallel reflection coefficients, ku and kv are arbitrary unit direction vectors orthonormal to the incident ray direction k, and n is the surface normal. For an incident wave in vacuum, the corresponding Fresnel reflection coefficients are"},{"citing_arxiv_id":"2605.01777","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Data driven approach for Outdoor Channel Prediction in 5G and Beyond","primary_cat":"eess.SP","submitted_at":"2026-05-03T08:28:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"Linear regression on ray-tracing data predicts 7 GHz outdoor channel coefficients with MAE 7.5155e-5 and RMSE 9.2861e-5, beating SVR and decision-tree regression.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17362","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FARM: Foundational Aerial Radio Map for Intelligent Low-Altitude Networking","primary_cat":"eess.SP","submitted_at":"2026-04-19T10:17:47+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":"2604.14869","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"An Open-Source Hardware-Aware Sub-THz Radio-Stripe Simulator","primary_cat":"eess.SP","submitted_at":"2026-04-16T11:01:45+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"The paper provides an open-source configuration-driven simulator for sub-THz radio-stripe architectures that includes models for polymer microwave fiber, couplers, and configurable RF impairments.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19803","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications Algorithms","primary_cat":"cs.AI","submitted_at":"2026-04-11T04:57:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"An LLM-powered agentic framework autonomously designs competitive and sometimes superior explainable algorithms for wireless PHY and MAC layer tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.06882","ref_index":51,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Telecom World Models: Unifying Digital Twins, Foundation Models, and Predictive Planning for 6G","primary_cat":"cs.RO","submitted_at":"2026-04-08T09:41:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Telecom World Models introduce a three-layer architecture for learned, action-conditioned, uncertainty-aware modeling of 6G network dynamics, combining digital twins and foundation models, with a network slicing proof-of-concept showing improved KPI prediction over baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.05860","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CommUNext: Deep Learning-Based Cross-Band and Multi-Directional Signal Prediction","primary_cat":"cs.IT","submitted_at":"2025-11-08T05:28:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A unified deep learning model predicts FR3 signal strength from FR1 data and sparse measurements to cut simulation and measurement costs in 6G networks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}