Pith. sign in

REVIEW 3 major objections 3 minor 37 references

Spectroscopy confirms ω Centauri's tidal tails and shows continuous kinematics and metallicity from the bound cluster into the debris.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.5

2026-07-12 16:08 UTC pith:SGL6YNOR

load-bearing objection Solid spectroscopic follow-up of ω Cen’s periphery and tails, but we only have the abstract—the attached full text is the wrong paper—so the membership claims cannot be audited yet. the 3 major comments →

arxiv 2605.23474 v2 pith:SGL6YNOR submitted 2026-05-22 astro-ph.GA

Disruption of a Giant: Spectroscopic Identification of Members in the Periphery and Tidal Tails of ω Centauri

P. B. Kuzma , A. M. N. Ferguson , A. L. Varri , P. Bianchini This is my paper
classification astro-ph.GA
keywords omega Centauriglobular clusterstidal tailsspectroscopic membershipFimbulthul streamMilky Way haloVLT/FLAMES
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Omega Centauri is the most complex of the Milky Way's globular clusters, and recent imaging claimed it has long tidal tails. This paper puts those claims on a spectroscopic footing. Using Bayesian target selection and VLT/FLAMES spectra across six fields spanning six degrees on the sky, the authors confirm 157 cluster members from line-of-sight velocity and metallicity, a 93 percent success rate. Five of those members lie in the debris out to 3.2 degrees from the cluster centre, with additional lower-probability candidates. The kinematics and metallicities of the new members join smoothly onto those of the bound cluster, and the metallicities match those reported for the Fimbulthul stream already linked to ω Cen. The work shows that wide-field multi-object spectroscopy can turn photometric debris candidates into securely identified tidal material.

Core claim

The authors spectroscopically confirm 157 members of ω Centauri (93 percent overall success) and identify five members in the tidal debris out to a cluster-centric radius of 3.2 degrees, plus lower-probability candidates. Analysis of the new members shows continuity of line-of-sight kinematics and metallicities from the bound cluster into the debris, with metallicities broadly consistent with the Fimbulthul stream.

What carries the argument

Bayesian-selected VLT/FLAMES spectroscopy: targets chosen by a Bayesian inference technique are confirmed as members from measured line-of-sight velocity and [Fe/H], converting photometric periphery and tail candidates into a kinematically and chemically vetted sample.

Load-bearing premise

The 93 percent success rate and the debris membership rest on the Bayesian target-selection pipeline and on the velocity and metallicity cuts used to separate cluster stars from field contaminants; if those cuts or the contamination model are biased, the debris and continuity claims weaken.

What would settle it

Independent spectroscopy of the same or adjacent fields that fails to recover the five reported debris members at the claimed velocities and metallicities, or that finds the outer sample is dominated by field interlopers rather than continuous with the bound cluster.

Watch this falsifier — get emailed when new claim-graph text bears on it.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

3 major / 3 minor

Summary. The manuscript reports a VLT/FLAMES spectroscopic survey of the outer regions of ω Centauri, with targets selected by a Bayesian inference technique across six fields spanning six degrees. From line-of-sight velocities and [Fe/H], the authors confirm 157 cluster members (93% success rate), identify five members in tidal debris out to 3.2 deg cluster-centric radius plus lower-probability candidates, and argue for kinematic and metallicity continuity from the bound cluster into the debris, with metallicities broadly consistent with the Fimbulthul stream. The work is framed as both a membership/characterisation study of ω Cen’s periphery and a demonstration of wide-field multi-object spectroscopy for GC tidal structures.

Significance. If the membership, debris detections, and continuity claims hold under a well-controlled selection function and contamination model, the paper would be a useful observational contribution: spectroscopic confirmation of ω Cen tidal tails remains limited, and a clean link to Fimbulthul would strengthen the disruption picture of this atypical cluster. The reported 93% targeting success and multi-degree spatial coverage would also be of practical interest for planning surveys with forthcoming wide-field spectrographs. The abstract’s claims are scientifically coherent for this subfield; significance hinges on transparent membership criteria and field-star control rather than on a novel theoretical result.

major comments (3)
  1. Only the abstract of the stated ω Cen paper is available for assessment; the supplied full-text body is a mismatched wireless-communications manuscript (ComHymba). Load-bearing elements for the central claims—velocity and [Fe/H] membership windows, Bayesian selection inputs/thresholds, field contamination model, error budgets, and the member catalog—cannot be audited. Until the correct full manuscript is provided, the 157-member sample, 93% success rate, five debris members, and continuity/Fimbulthul statements cannot be verified.
  2. Abstract methods claim: membership and the 93% success rate rest on Bayesian target selection plus LOS-velocity and [Fe/H] confirmation. The full paper must define the acceptance windows, prior/probability threshold, and how the selection function is corrected (or shown not to bias debris membership). Without that, spectroscopic “confirmation” can partly re-confirm a photometry/astrometry-pre-enriched sample, weakening the debris and continuity claims.
  3. Abstract debris claim (five members to 3.2 deg, plus lower-probability candidates): the paper must quantify interloper probability per star, show spatial/kinematic association with the reported tails (not only cluster-like v_los and [Fe/H]), and separate secure members from candidates with explicit criteria. Continuity of kinematics and metallicity into the debris needs quantitative comparison (e.g., distributions or trends with radius), not only qualitative consistency.
minor comments (3)
  1. Abstract: “six degrees across the sky” vs “3.2 deg” cluster-centric radius should be clarified (field layout vs maximum member radius).
  2. Abstract: “broadly consistent” with Fimbulthul should be backed by a quantitative metallicity comparison (means, dispersions, or KS-type test) once the correct full text is available.
  3. Abstract: define or cite the Bayesian selection technique and the FLAMES setup (resolution, wavelength coverage, RV/[Fe/H] precision) for reproducibility.

Circularity Check

0 steps flagged

No significant circularity; the provided manuscript (mismatched wireless foundation-model text) and the ω Cen abstract contain no derivation that reduces a claimed prediction or first-principles result to its own inputs by construction.

full rationale

The target abstract is an observational membership study: targets are selected by a Bayesian technique, then independently confirmed via measured line-of-sight velocities and [Fe/H], yielding a 93% success rate, five debris members to 3.2 deg, and reported kinematic/metallicity continuity. Confirmation quantities are spectroscopic observables, not algebraic rearrangements of the selection priors, so the membership and continuity claims are not forced by definition. The CACHEABLE full-text body is an entirely different paper (ComHymba, a masked-autoencoder wireless foundation model). That manuscript proposes an architecture (3D patchification, Hymba hybrid blocks, domain-informed masking, amplitude–phase loss), pre-trains it, and reports empirical NMSE/MAE/accuracy gains on eight downstream tasks against external baselines. No equation equates a “prediction” to a fitted parameter of the same quantity; no uniqueness theorem is imported from overlapping authors to forbid alternatives; no ansatz is smuggled via self-citation as a forced result. Standard self-citations to prior work (MAE, RoPE, Mamba, etc.) are ordinary background and do not load-bear the central empirical claims. Because no quoted reduction of the form “Eq. X ≡ input by construction” exists, the circularity score is 0 and the steps list is empty. Mild selection-bias risk in membership studies is a correctness/robustness concern, not circularity under the stated criteria.

Axiom & Free-Parameter Ledger

2 free parameters · 4 axioms · 0 invented entities

Abstract-only ledger for an observational membership paper. Load-bearing premises are standard astrophysical assumptions (LOS velocity and [Fe/H] as membership discriminants; tidal debris continuous with the progenitor) plus the paper-specific Bayesian selection and unstated numerical cuts. No free parameters or invented entities can be extracted beyond those implied by the abstract.

free parameters (2)
  • Membership velocity and [Fe/H] acceptance windows
    Abstract confirms members via LOS velocity and [Fe/H] but does not state the numerical cuts or probability thresholds; those choices directly set the 157-member sample and 93% success rate.
  • Bayesian selection prior / probability threshold for targeting
    Targets are chosen with a Bayesian inference technique; the prior and cut that define the input sample are free design choices that control purity and the claimed success rate.
axioms (4)
  • domain assumption Line-of-sight velocity and [Fe/H] jointly suffice to confirm ω Cen membership against field contamination in the surveyed fields.
    Core confirmation method stated in the abstract; standard in GC spectroscopy but depends on field density and measurement precision not given here.
  • domain assumption Stars at large cluster-centric radius with matching kinematics/chemistry are tidal debris continuous with the bound cluster rather than unrelated halo stars or a separate population.
    Underpins the continuity and tidal-tail interpretation in the abstract.
  • domain assumption Metallicity consistency with the Fimbulthul stream supports a physical association with ω Cen.
    Abstract claims broad consistency with Fimbulthul; association is interpretive and relies on prior stream–cluster linkage.
  • ad hoc to paper Bayesian inference on (unspecified) photometric/astrometric inputs yields an unbiased enough target list for a meaningful 93% spectroscopic success rate.
    Paper-specific selection pipeline; details absent from abstract.

pith-pipeline@v1.1.0-grok45 · 21855 in / 2827 out tokens · 28873 ms · 2026-07-12T16:08:58.966390+00:00 · methodology

0 comments
read the original abstract

$\omega$ Centauri ($\omega$ Cen, NGC\,5139) is one of the most enigmatic globular clusters in the Milky Way, with the recent detection of tidal tails adding further to its complexity. We report the results of a spectroscopic study of stars in the outer regions of $\omega$ Cen, which provides an improved characterisation of the cluster periphery and confirms the existence of tidal tails. Our targets, which lie in six VLT/FLAMES fields sampling six degrees across the sky, are selected using a Bayesian inference technique. We confirm 157 members of $\omega$ Cen based on line-of-sight velocity and [Fe/H] measurements, indicating an overall success rate of 93 per cent. We trace stars along the tidal tails to a cluster-centric radius of 3.2~deg, identifying five members in the debris and additional lower-probability candidates. The analysis of the kinematics and metallicities of the new members provides evidence of continuity in these properties from the bound component of the progenitor cluster into its tidal debris. We find that the metallicities of stars in the peripheral regions and tidal tails of $\omega$ Cen are broadly consistent with those in the \textit{Fimbulthul} stream to which the cluster has been previously linked. Our study provides a glimpse of the promise of new and forthcoming wide-field multi-object spectrographs for advancing understanding of tidal structures around Milky Way globular clusters.

Figures

Figures reproduced from arXiv: 2605.23474 by A. L. Varri, A. M. N. Ferguson, P. Bianchini, P. B. Kuzma.

Figure 1
Figure 1. Figure 1: Left: Locations of our six fields (white circles) overlayed on a optical image cutout of 𝜔 Cen from DR3 (Gaia Collaboration et al. 2023). Additionally, we have included the contours of the tidal tails from K21, and the tidal (Jacobi) radii through inner (outer) yellow dashed circles (46.4 and 106.9 arcmin respectively Balbinot & Gieles 2018; de Boer et al. 2019) We indicate the direction of the trailing an… view at source ↗
Figure 2
Figure 2. Figure 2: Diagnostic plots showing [Fe/H] against Vh for each observed field along the stream, denoted in the lower left of each panel. Each target has been colour coded by their respective probabilities, with white corresponding to the lowest membership probability, and dark red corresponding to the highest. Additionally, the BHB stars selected for observation are shown in cyan. The vertical shaded region indicates… view at source ↗
Figure 3
Figure 3. Figure 3: Diagnostic plots demonstrating the CMD for each observed field along the stream, denoted in the upper right of each figure. The large points indicate the 155 𝑃mem > 0.3 targets we identify as potential 𝜔 Cen members and are coloured according to their Pmem value. Cyan points are the confirmed BHB candidates, and the white points are the rest of the observed stars. In each figure, we have the CMD of 𝜔 Cen f… view at source ↗
Figure 4
Figure 4. Figure 4: Proper motion distribution of the Pmem ≤ 0.3 stars (white) that have consistent [Fe/H] and line-of-sight velocities with the nominated 𝜔 Cen members, which have Pmem > 0.3 (red). 23 of the former stars are consistent with the high-probability members. 4 CONCLUSION In this paper, we present VLT/FLAMES spectroscopic observations of candidate members in the peripheral regions and tidal tails of the massive GC… view at source ↗
Figure 5
Figure 5. Figure 5: Vh and [Fe/H] as a function of position along the direction of the 𝜔 Cen tidal tails, denoted by 𝑥 ′′. The horizontal shaded regions in both panels are the same as those in [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Metallicity distribution of our 𝑃𝑚𝑒𝑚 > 0.3 stars as a function of radius, with the PGS sample from Kuzma & Ishigaki (2025) overlaid. The vertical dashed lines indicate the tidal and Jacobi radii of 𝜔 Cen. likely due to a sampling issue related to the target brightness of the two surveys. While we have presented the most extensive spectroscopic study yet of the outer regions of 𝜔 Cen, our VLT/FLAMES fields … view at source ↗

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

37 extracted references · 5 linked inside Pith

  1. [1]

    The road towards 6G: A comprehensive survey,

    W. Jiang, B. Han, M. A. Habibi, and H. D. Schotten, “The road towards 6G: A comprehensive survey,”IEEE Open J. Commun. Soc., vol. 2, pp. 334–366, Feb. 2021

    2021

  2. [2]

    Large AI models for wireless physical layer,

    J. Guo, Y . Cui, S. Jin, and J. Zhang, “Large AI models for wireless physical layer,”IEEE Commun. Mag., vol. 64, no. 5, pp. 148–155, 2026

    2026

  3. [3]

    Signal processing and learning for next generation multiple access in 6G,

    W. Chen, Y . Liu, H. Jafarkhani, Y . C. Eldar, P. Zhu, and K. B. Letaief, “Signal processing and learning for next generation multiple access in 6G,”IEEE J. Sel. Topics Signal Process., vol. 18, no. 7, pp. 1146–1177, Oct. 2024

    2024

  4. [4]

    A comprehensive survey on GenAI-enabled 6G: Technologies, challenges, and future research avenues,

    M. Sheraz, T. C. Chuah, W. U. K. Tareen, A. Al-Habashna, S. I. Saeed, M. Ahmed et al., “A comprehensive survey on GenAI-enabled 6G: Technologies, challenges, and future research avenues,”IEEE Open J. Commun. Soc., vol. 6, pp. 4563–4590, 2025

    2025

  5. [5]

    A comprehensive survey of large AI models for future communications: Foundations, applications, and challenges,

    F. Jiang, C. Pan, L. Dong, K. Wang, M. Debbah, D. Niyato, and Z. Han, “A comprehensive survey of large AI models for future communications: Foundations, applications, and challenges,”IEEE Commun. Surv. Tuto- rials, vol. 28, pp. 4731–4764, 2026

    2026

  6. [6]

    An introduction to deep learning for the physical layer,

    T. J. O’Shea and J. Hoydis, “An introduction to deep learning for the physical layer,”IEEE Trans. Cognit. Commun. Networking, vol. 3, no. 4, pp. 563–575, Dec. 2017

    2017

  7. [7]

    Deep learning for intelligent wireless networks: A comprehensive survey,

    Q. Mao, F. Hu, and Q. Hao, “Deep learning for intelligent wireless networks: A comprehensive survey,”IEEE Commun. Surv. Tutorials, vol. 20, no. 4, pp. 2595–2621, 2018

    2018

  8. [8]

    AI- driven wireless positioning: Fundamentals, standards, state-of-the-art, and challenges,

    G. Pan, Y . Gao, Y . Gao, W. Yu, Z. Zhong, X. Yanget al., “AI- driven wireless positioning: Fundamentals, standards, state-of-the-art, and challenges,”IEEE Commun. Surv. Tutorials, vol. 28, pp. 4394–4428, 2026

    2026

  9. [9]

    Advancing 6G: Survey for explainable AI on communications and network slicing,

    H. Sun, Y . Liu, A. Al-Tahmeesschi, A. Nag, M. Soleimanpour, B. Canberk, H. Arslan, and H. Ahmadi, “Advancing 6G: Survey for explainable AI on communications and network slicing,”IEEE Open J. Commun. Soc., vol. 6, pp. 1372–1412, 2025

    2025

  10. [10]

    Wireless large AI model: shaping the AI-empowered future of 6G and beyond,

    F. Zhuet al., “Wireless large AI model: shaping the AI-empowered future of 6G and beyond,” 2026, arXiv:2504.14653. [Online]. Available: https://arxiv.org/abs/2504.14653

    Pith/arXiv arXiv 2026

  11. [11]

    Big AI models for 6G wireless networks: Opportunities, challenges, and research directions,

    Z. Chen, Z. Zhang, and Z. Yang, “Big AI models for 6G wireless networks: Opportunities, challenges, and research directions,”IEEE Wireless Commun., vol. 31, no. 5, pp. 164–172, Oct. 2024

    2024

  12. [12]

    Large language models for wireless communications: From adaptation to autonomy,

    L. Lianget al., “Large language models for wireless communications: From adaptation to autonomy,”arXiv preprint arXiv:2507.21524, 2025

    arXiv 2025

  13. [13]

    ST-LLM: Multi-scenario adaptation and multi-task learning wireless large language model,

    W. Chen, B. Yang, J. Cheng, and B. Ai, “ST-LLM: Multi-scenario adaptation and multi-task learning wireless large language model,”Sci. China Inf. Sci., 2026

    2026

  14. [14]

    Towards channel foundation models (CFMs): Motivations, methodologies and opportunities,

    J. Jiang, Y . Gao, X. Wu, and S. Xu, “Towards channel foundation models (CFMs): Motivations, methodologies and opportunities,”arXiv preprint arXiv:2507.13637, 2025

    Pith/arXiv arXiv 2025

  15. [15]

    WiFo: Wireless foundation model for channel prediction,

    B. Liu, S. Gao, X. Liu, X. Cheng, and L. Yang, “WiFo: Wireless foundation model for channel prediction,”Sci. China Inf. Sci., vol. 68, no. 6, p. 162302, 2025

    2025

  16. [16]

    WirelessGPT: A generative pre-trained multi-task learning framework for wireless communication,

    T. Yang, P. Zhang, M. Zheng, Y . Shi, L. Jing, J. Huang, and N. Li, “WirelessGPT: A generative pre-trained multi-task learning framework for wireless communication,”IEEE Network, vol. 39, no. 5, pp. 58–65, 2025

    2025

  17. [17]

    ChannelGPT: A large model toward real-world channel foundation model for 6G en- vironment intelligence communication,

    L. Yu, L. Shi, J. Zhang, Z. Zhang, Y . Zhang, and G. Liu, “ChannelGPT: A large model toward real-world channel foundation model for 6G en- vironment intelligence communication,”IEEE Commun. Mag., vol. 63, no. 10, pp. 68–74, Oct. 2025

    2025

  18. [18]

    LVM4CSI: Enabling direct application of pre-trained large vision models for wireless channel tasks,

    J. Guo, P. Jiang, C.-K. Wen, S. Jin, and J. Zhang, “LVM4CSI: Enabling direct application of pre-trained large vision models for wireless channel tasks,”arXiv preprint arXiv:2507.05121, 2025

    Pith/arXiv arXiv 2025

  19. [19]

    LWM: A pre-trained wireless foundation model for universal feature extraction,

    S. Alikhani, G. Charan, and A. Alkhateeb, “LWM: A pre-trained wireless foundation model for universal feature extraction,” inProc. IEEE Int. Conf. Mach. Learn. Commun. Netw., 2025, pp. 1–6

    2025

  20. [20]

    Efficient Transformers: A Survey,

    Y . Tay, M. Dehghani, D. Bahri, and D. Metzler, “Efficient Transformers: A Survey,”ACM Comput. Surv., vol. 55, no. 6, pp. 1–28, 2022

    2022

  21. [21]

    Masked autoencoders are scalable vision learners,

    K. He, X. Chen, S. Xie, Y . Li, P. Doll ´ar, and R. Girshick, “Masked autoencoders are scalable vision learners,” inProc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., 2022, pp. 15979–15988

    2022

  22. [22]

    Hymba: A hybrid-head architecture for small language models,

    X. Donget al., “Hymba: A hybrid-head architecture for small language models,” inProc. Int. Conf. Learn. Represent., 2025, pp. 1–23

    2025

  23. [23]

    Attention is all you need,

    A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” inProc. Adv. Neural Inf. Process. Syst., 2017, pp. 5998–6008

    2017

  24. [24]

    Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality,

    T. Dao and A. Gu, “Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality,”Proc. Mach. Learn. Res., vol. 235, pp. 10041–10071, 2024. [25]Study on channel model for frequencies from 0.5 to 100 GHz (Release 16), 3GPP Technical report (TR) 38.901, Dec. 2019, v16.1.0

    2024

  25. [25]

    QuaDRiGa: A 3- D multi-cell channel model with time evolution for enabling virtual field trials,

    S. Jaeckel, L. Raschkowski, K. B ¨orner, and L. Thiele, “QuaDRiGa: A 3- D multi-cell channel model with time evolution for enabling virtual field trials,”IEEE Trans. Antennas Propag., vol. 62, no. 6, pp. 3242—3256, Jun. 2014

    2014

  26. [26]

    Deep learning for mmWave beam and blockage prediction using sub-6 GHz channels,

    M. Alrabeiah and A. Alkhateeb, “Deep learning for mmWave beam and blockage prediction using sub-6 GHz channels,”IEEE Trans. Commun., vol. 68, no. 9, pp. 5504–5518, Sep. 2020

    2020

  27. [27]

    CSI-based fingerprinting for indoor localization: A deep learning approach,

    X. Wang, L. Gao, S. Mao, and S. Pandey, “CSI-based fingerprinting for indoor localization: A deep learning approach,”IEEE Trans. Veh. Technol., vol. 66, no. 1, pp. 763–776, Jan. 2017

    2017

  28. [28]

    Deep UL2DL: Data- driven channel knowledge transfer from uplink to downlink,

    M. S. Safari, V . Pourahmadi, and S. Sodagari, “Deep UL2DL: Data- driven channel knowledge transfer from uplink to downlink,”IEEE Open J. Veh. Technol., vol. 1, pp. 29–44, 2020

    2020

  29. [29]

    CSI-based MIMO indoor positioning using attention-aided deep learning,

    R. Wan, Y . Chen, S. Song, and Z. Wang, “CSI-based MIMO indoor positioning using attention-aided deep learning,”IEEE Commun. Lett., vol. 28, no. 1, pp. 53–57, Jan. 2024

    2024

  30. [30]

    Deep learning for fading channel predic- tion,

    W. Jiang and H. D. Schotten, “Deep learning for fading channel predic- tion,”IEEE Open J. Commun. Soc., vol. 1, pp. 320–332, Mar. 2020

    2020

  31. [31]

    Empirical evaluation of gated recurrent neural networks on sequence modeling,

    J. Chung, C. Gulcehre, K. Cho, and Y . Bengio, “Empirical evaluation of gated recurrent neural networks on sequence modeling,”arXiv preprint arXiv:1412.3555, 2014

    Pith/arXiv arXiv 2014

  32. [32]

    Attention aided CSI wireless localization,

    A. Salihu, S. Schwarz, and M. Rupp, “Attention aided CSI wireless localization,” inProc. IEEE Int. Workshop Signal Process. Adv. Wireless Commun., 2022, pp. 1–5

    2022

  33. [33]

    Accurate channel prediction based on transformer: Making mobility negligible,

    H. Jiang, M. Cui, D. W. K. Ng, and L. Dai, “Accurate channel prediction based on transformer: Making mobility negligible,”IEEE J. Sel. Areas Commun., vol. 40, no. 9, pp. 2717–2732, Sep. 2022

    2022

  34. [34]

    LLM4CP: Adapting large language models for channel prediction,

    B. Liu, X. Liu, S. Gao, X. Cheng, and L. Yang, “LLM4CP: Adapting large language models for channel prediction,”J. Commun. Inf. Net- works, vol. 9, no. 2, pp. 113–125, Jun. 2024

    2024

  35. [35]

    LLM4WM: Adapting LLM for wireless multi-tasking,

    X. Liu, S. Gao, B. Liu, X. Cheng, and L. Yang, “LLM4WM: Adapting LLM for wireless multi-tasking,”IEEE Trans. Mach. Learn. Commun. Networking, vol. 3, pp. 835–847, 2025

    2025

  36. [36]

    HELENA: High-efficiency learning-based channel estimation using dual neural attention,

    M. C. Botero, E. A. Beyazit, N. Slamnik-Krijestorac, and J. M. Marquez- Barja, “HELENA: High-efficiency learning-based channel estimation using dual neural attention,”arXiv preprint arXiv:2506.13408, 2025

    Pith/arXiv arXiv 2025

  37. [37]

    Millimeter wave beam-selection using out-of-band spatial information,

    A. Ali, N. Gonz ´alez-Prelcic, and R. W. Heath, Jr., “Millimeter wave beam-selection using out-of-band spatial information,”IEEE Trans. Wireless Commun., vol. 17, no. 2, pp. 1038–1052, Feb. 2018

    2018