arXiv_SD
-
Beyond Encoder Fusion: Multi-View Discrete Token Augmentation for LLM-Based ASR
2026-09-20 10:19:46Paul Mo\"ise Gangbadja, Mickael Rouvier, Fabrice Lef\`evreAbstract
Discrete speech tokens provide a compact interface between speech encoders and large language models for automatic speech recognition, but single-tokenization systems remain sensitive to the chosen encoder. We propose multi-view discrete token augmentation, a simple strategy that augments each training utterance by generating alternative token sequences from fixed SSL encoders, such as HuBERT, WavLM, and MMS-300M. These tokenizations are treated as complementary training views for a shared LLM decoder, exposing it to more diverse discrete speech representations without requiring multi-encoder inference. At test time, the model can operate with a single encoder. On LibriSpeech, the approach consistently improves all encoders over independently trained baselines, with WavLM reaching 3.30% WER on test-clean and 8.13% on test-other. Budget-matched controls show that the gains come from encoder diversity rather than data volume. ROVER over multi-view hypotheses further improves WER to 3.03% and 7.38%.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23525
PDF
-
LiteCASS: A Lightweight End-to-End Network for Real-Time Stereo Cinematic Audio Source Separation
2026-09-20 08:31:26Yuanxin Guo, Qiang Ji, Mengmei Liu, Yuhan Lv, Ningning Pan, Gongping HuangAbstract
Cinematic audio source separation (CASS) decomposes a soundtrack into dialogue, music, and sound-effects (SFX) stems. Existing CASS methods, however, suffer from two critical limitations: they rely on heavily parameterized network architectures and GPU-class hardware, limiting their use in real-time and resource-constrained scenarios, and they are overwhelmingly designed for monaural signals, leaving the stereo scenario largely unexplored. We present LiteCASS, to our knowledge the first lightweight end-to-end network for real-time stereo CASS. LiteCASS combines deterministic STFT subband rearrangement with two jointly trained compact U-Nets: the first extracts dialogue, and the second separates music and SFX from the predicted non-speech component. A multi-task waveform-domain L1 loss supervises all stems. On a spatialized stereo extension of DnR v3, LiteCASS-K8 uses only 1.06M parameters and 0.72G MACs per second, while achieving the highest averaged SI-SDR among the compared CASS baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23453
PDF
-
Misrecognition or Abstraction? Rethinking Outputs of Sound Event Recognition
2026-09-20 06:55:47Naoya Tomida, Yuki Okamoto, Keisuke ImotoAbstract
Conventional general sound recognition systems typically output deterministic sound event labels, implicitly assuming that the target sound class can be correctly identified from the input audio. However, in real listening situations, the sound event class is not always clearly identifiable. Human listeners may nevertheless understand their surroundings from an ambiguous sound without identifying its exact sound event class. This motivates a discussion of how the outputs of sound recognition systems should be redesigned under such uncertainty. As a basis for this discussion, this paper proposes an output representation for sound event recognition that combines a sound event class, its confidence score, and an onomatopoeic description of the sound. The proposed representation preserves conventional class-based recognition while providing an additional onomatopoeic description of acoustic characteristics that can remain informative even when the class prediction is uncertain. Experiments using ESC-50 and ESC-50-Onomatopoeia show that the proposed method achieves sound recognition performance comparable to that of a conventional recognition-only system. In addition, an LLM-as-a-judge evaluation and subjective listening experiments indicate that the proposed output is preferred over conventional deterministic outputs based on the sound event label, particularly when used to support understanding of the surrounding environment. These results suggest that such output representations can make sound event recognition more informative and communicative under uncertainty.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23411
PDF
-
OmniEcho: Spatial Audio Understanding for Embodied Agents
2026-09-20 06:45:31Ruixun Liu, Yuxuan Wang, Jiacheng Xie, Yuhuan You, Donghua Cai, Junming Lin, Xiong-Hui Chen, Zhifang Guo, Yunfei Chu, Qize Yang, Xize Cheng, Jin Xu, Yiwu ZhongAbstract
Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challenging for embodied agents. In particular, it is still unclear how to effectively evaluate and model spatial audio understanding in embodied settings. To address this gap, we introduce \textbf{OmniEchoBench}, a unified benchmark for spatial audio-visual perception and audio-vision-language navigation. OmniEchoBench comprises six tasks over 197 real-world spatial audio-visual scenes, 2,972 question-answer pairs, and 900 navigation samples with first-order ambisonics (FOA) audio collected from 30 real-world environments. To enable scalable training supervision, we develop a controllable rendering pipeline for spatial audio. It preserves geometric consistency among sound sources, visual observations, and agent trajectories. Building on this, we propose \textbf{OmniEcho}, a spatially aware omni-modal model. It introduces an FOA spatial encoder alongside a pretrained semantic audio pathway. Extensive experiments show that OmniEcho achieves state-of-the-art performance on spatial audio-visual perception. For our sound-guided navigation, OmniEcho reaches a performance level close to that of traditional vision-language navigation. These results demonstrate that spatial audio can serve as a valuable signal for embodied scene reasoning and navigation, while also highlighting fine-grained spatial localization and distance estimation as important open challenges.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23407
PDF
-
Low-Rank Frequency Convolution and Noise-Range Augmentation for Real-Time Pitch Estimation on Edge Devices
Abstract
Pitch estimation on an edge device is constrained in three ways at once. The model must be small, it must stay accurate when the input is noisy, and one frame must be produced inside the frame period. In this report the Frequency Convolution Network (FrCN) of our earlier work is factored into a low-rank form. The number of parameters is reduced by 35.9%, from 17,787 to 11,397, and accuracy is not reduced, either in domain or on two corpora the model was never trained on. The range of the noise used during training is also shown to dominate the architecture in setting how the model behaves when the interference is severe. When the training noise floor is lowered from +6.02 dB to -20 dB, 0.35 points of clean RPA50 are lost and RPA50 at -20 dB is raised from 2.44 to 22.41. This effect is about two orders of magnitude larger than any architectural effect that was measured. The semi-orthogonal constraint used in TDNN-F is found to be redundant with the normalization inside the bottleneck, and accuracy is reduced when both are applied. Whether the factorization saves time depends on the runtime: in eager PyTorch the factored model is 45% slower, while in a compiled kernel it is 15% faster. For deployment, a small C kernel was written. It needs 83 kB on disk and no runtime library beyond libc and libm. It is faster than OpenBLAS on all four CPUs that were tested, faster than ONNX Runtime by 3.8 times, and faster than PyTorch by 13 times. Its output was checked against PyTorch on 271,893 held-out frames per model, and the same pitch bin was selected on every one of them.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23340
PDF
-
EquiSELD: Efficient training of equivariant sound event localization and detection networks
2026-09-19 17:51:24Goksenin Yuksel, Marcel van Gerven, Kiki van der HeijdenAbstract
First-order Ambisonics (FOA) signals exhibit exact O(3) symmetry: The rotation or reflection of the FOA signal modifies the direction of arrival of the sound sources, while preserving the sound sources themselves. Prior attempts to utilize this spatial symmetry of FOA to improve the efficiency and robustness of sound event detection and localization (SELD) systems either learned only an approximation of the symmetry through rotation-based augmentation or relied on computationally expensive methods to integrate equivariance. Furthermore, prior work focused exclusively on SO(3) equivariance , leaving the potential of incorporating O(3) equivariance for SELD tasks unclear. To address these limitations, we developed EquiSELD. This equivariant attention network processes first-order Ambisonics as paired streams of O(3)-invariant scalars and equivariant intensity vectors, producing an invariant activity magnitude and an equivariant DOA with a Multi-ACCDOA readout. To compare the impact of O(3) versus SO(3)-equivariance, we designed a matched SO(3)-only variant. EquiSELD outperforms prior equivariant networks on both simulated scenes with measured RIRs and recordings of real-world sound scenes at a fraction of the training cost. EquiSELD additionally surpasses the performance of non-equivariant SELD networks of a similar size on the simulated real-world sound scenes and achieves competitive performance on the real-world sound scenes.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23156
PDF
-
Bearings: Self-Supervised Soundfield Embeddings from First-Order Ambisonics
2026-09-19 17:40:28Goksenin Yuksel, Marcel van Gerven, Kiki van der HeijdenAbstract
Recently proposed self-supervised audio encoders learn powerful general-purpose representations of sound scenes, yet they are spatially blind. To supply the missing spatial representation of sound scenes, we introduce Bearings. Bearings is a self-supervised framework that learns soundfield embeddings from unlabeled first-order Ambisonics. We pre-train a masked auto-encoder paired with a decoder conditioned on frozen acoustic embeddings from an off-the-shelf single-channel audio encoder. Our results show that the resulting soundfield embeddings form a reusable stream that can be attached to frozen acoustic encoders with a lightweight trainable fusion head. On sound event localization and detection, concatenating our soundfield embeddings with acoustic representations provides the missing spatial information and enables joint detection and localization, raising the location-dependent F-score from below 4 to 50 on TAU-NIGENS 2021 and 39 on STARSS23. To our knowledge, Bearings is the first self-supervised soundfield encoder whose embeddings plug into frozen acoustic encoders without retraining either model.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23152
PDF
-
Discrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs
2026-09-19 07:46:24Jing Peng, Zichao Nie, Zhisheng Zhang, Jingran Xie, Zhiyong Wu IDAbstract
Large Audio Language Models (LALMs) utilize either continuous features or discrete tokens, yet the optimal representation paradigm for general audio understanding remains debated. Existing benchmarks often focus on narrow domains or evaluate encoders outside LALM contexts. To address these gaps, we systematically evaluate continuous and discrete representations across speech, sound and music. Utilizing our UniARC framework with dual evaluation strategies across model scales from SmolLM2-135M to Llama-3-8B, we analyze the dynamic relationships of data volume, model capacity, and computational efficiency. Our results reveal the pivotal role of semantic constraints in tokenization for audio understanding and demonstrate that scaling backbones fail to compensate for information loss in audio representation, especially in data-limited tasks. These findings offer practical guidance for balancing semantic density, fidelity, and efficiency in future LALMs.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22851
PDF
-
ParA-LLM: A Unified Approach to Paralinguistic and Acoustic Speech Understanding
2026-09-19 05:08:58Nishit Anand, Jiaqi Su, Ke Chen, Yunyun Wang, Dinesh Manocha, Ramani Duraiswami, Rithesh Kumar, Zeyu JinAbstract
Recent advances in Audio LLMs have achieved human-level speech recognition, yet existing systems struggle to capture paralinguistic aspects such as speaker traits, expressive variations, and environmental acoustic conditions. To address this, we design a framework of 22 paralinguistic characteristics and create a dataset of over 1.2M Audio-QA pairs. We develop ParA-LLM, trained with a two-stage curriculum: first on single-attribute questions to build foundational knowledge, then on multi-attribute questions for joint reasoning over speaker and acoustic characteristics. We also release ParA-Bench, a benchmark of 6,000 multiple-choice questions across speaker-speech, acoustic, and mixed categories, where frontier models like GPT-4o-Audio achieve only 36% accuracy. ParA-LLM surpasses state-of-the-art Audio LLMs like GPT-4o-Audio by 7.5% on ParA-Bench, with additional gains of 1.13% on MMAU-Pro Speech and 7.49% on MMAR Speech.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22771
PDF
-
SEABED: SouthEast Asian Benchmark for Evaluating Audio Reasoning
2026-09-18 21:11:17Harshit Rajgarhia, Asif Shaik, Rachuri Lokesh, Sushanta Kumar Pani, Abhishek MukherjiAbstract
Modern audio-language models are no longer judged only on what words they can transcribe, but on whether they can reason over what they hear: recovering meaning that lives in tone and prosody, telling dialects and regional languages apart, and resolving ambiguity that the written form leaves open. This capability is now measured by a growing family of audio-reasoning benchmarks, but almost entirely in English and on general-domain audio. Southeast Asia (SEA) is served instead by benchmarks that inherit an English task taxonomy of recognition, translation, and paralinguistic classification, and therefore test whether a model hears SEA speech rather than whether it can reason from it. We introduce SEABED, an audio-first question answering dataset designed to benchmark language and audio reasoning models on SEA speech. SEABED comprises a suite of six audio-reasoning tasks built entirely from real, openly available SEA speech corpora, yielding 5,404 question-answer pairs. We evaluate six frontier and region-specific audio LLMs: even the state-of-the-art model Gemini 3.5 Flash achieves only 50.3% weighted average accuracy. SEABED evaluates not only answer accuracy, but also whether models' stated reasoning is grounded in the audio evidence. A sample of the benchmark data is available here: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22586
PDF
-
Spherical Harmonic Sliced Wasserstein Displacement Interpolation for Acoustic Source and Reflection Density Modeling
Abstract
Spatial room impulse responses (SRIRs) capture directional distributions of acoustic sound-sources and their reflections. However, collecting SRIRs of moving sound-sources remains a challenge, requiring complex interpolations across measurements that account for multi-path spatial-temporal dynamics. This paper investigates the Wasserstein metric and displacement for evaluating interpolated SRIR echo densities in the spherical harmonic domain. We present novel sum-of-magnitude square expansions for efficiently fitting probability density functions, maximizing likelihood, inverse sampling, and computing spherical sliced Wasserstein interpolations. Experiments compare the Wasserstein displacements and metric to linear and geometric interpolations of SRIR image-source densities on a line-path, and demonstrate model-order reduction.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22028
PDF
-
Investigating the Performance and Energy Costs of Replicating Band-Split RNN for Music Source Separation
2026-09-18 15:40:14Paul Magron, Romain Serizel, Constance DouwesAbstract
Band-split recurrent neural network (BSRNN) is a popular music source separation model that yields close to state-of-the-art results using reasonable computational resources and public datasets. It is therefore interesting from a reproducible research perspective, but achieving its performance is not straightforward since its full code is not available. In this paper, we conduct a replication of BSRNN via implementing the full pipeline. We extend the original paper's analysis by experimentally studying various design choices about data preprocessing, the optimization protocol, and architectural parameters. We report and discuss this project's energy cost, and we underline how its footprint could have been substantial lower upon availability of the full pipeline, which advocates for more reproducible research practices. To comply with this objective, we publicly release our code and pre-trained models.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21918
PDF
-
Training Music Sample Identification Models on Real Sample Pairs
2026-09-18 15:35:01R. Oguz Araz, Joan Serr\`a, Xavier Lizarraga-Seijas, Emilio Molina, Xavier Serra, Yuki Mitsufuji, Dmitry BogdanovAbstract
Sample identification (SI) is the task of matching pairs of tracks, where one track is created by musically transforming an element of the other. In the absence of sample annotations at scale, the dominant training paradigm has depended on artificially creating sample pairs. Although a recently released dataset provides annotations of real sample pairs at scale, an effective training recipe is missing. In this work, we present SI Embeddings (SIE), an SI model that achieves state-of-the-art results on three benchmarks, including a large-scale test set. We show that the previous state of the art trained on artificial pairs generalizes only partially to real pairs, and that its training data limits its performance. We also show that real pairs do not fully account for SIE's performance: its architecture and training recipe contribute substantially. We provide the first fully supervised training recipe for real-world SI, establishing a strong foundation for future research in the field.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21911
PDF
-
BLINC: Blind Calibration For Training-Free Speech Enhancement Adaptation
2026-09-18 15:26:30Tobias Raichle, Ekaterina Gavrilko, Bin YangAbstract
Speech enhancement (SE) models degrade under domain shifts and have to adapt to unseen target domains during deployment. Most existing test-time adaptation (TTA) methods for SE do so by adapting a subset of the model weights using a self-supervised loss, which requires backpropagation at test-time and permanently alters the model. We instead recalibrate the prediction itself and propose BLINC, a training-free TTA method that remaps the predicted time-frequency mask onto a bimodal target distribution by histogram matching. At test-time, the target distribution is parameterized from blind features of the noisy recording, so neither a reference distribution from a classical algorithm nor online metric optimization is involved. BLINC improves the overall quality of both evaluated SE models on almost every target condition and matches or exceeds the loss-based TTA baselines at minimal overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21898
PDF
-
GenTraceBench: A Benchmark for Tracing Audio Deepfakes Across Pre- and Post-training Stages
2026-09-18 13:15:52Li Wang, Kunyu Feng, Wan Lin, Dekun Chen, Qinke Ni, Xueyao Zhang, Lei Wang, Jie Shi, Haizhou Li, Zhizheng WuAbstract
Modern text-to-speech (TTS) systems are rarely deployed as unchanged pre-trained models. They are often adapted through supervised fine-tuning (SFT) or preference optimization such as DPO and GRPO. This raises a practical question for audio deepfake forensics: do fingerprints learned from a foundation generator remain valid after adaptation? We present GenTraceBench, a controlled benchmark spanning five TTS architectures, 16 pre-/post-training variants, and 49,728 utterances generated with fixed texts and speaker prompts. Under a train-on-foundation, test-on-adapted protocol, we evaluate binary detection, closed-set attribution, and open-set verification. DPO and GRPO generally preserve fingerprints, whereas some SFT and pre-training-data changes cause substantial drift; effect sizes vary across three forensic backbones. Repeated training runs confirm the largest W2V-BERT attribution drop, while a data-mixture control with comparable speech quality shows that composition change need not cause drift. In W2V-BERT verification, multi-shot enrollment reduces EER for the SFT condition from 44.4% to 11.0%, whereas the SingNet-only condition remains at or above 45% EER.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21738
PDF
-
Causal limits and optimal allocation for passive frequency-selective hearing protection
Abstract
Passive Helmholtz-resonator earplugs aim to attenuate hazardous noise while keeping speech audible; the air volume of an ear-sized shell is finite, and we treat it as the resource a design spends. For a vented bore transparent at zero frequency and loaded by reactive side branches, causality fixes a conserved integral of transmission loss. We derive it in device variables, add viscous and flanking constraints, and allocate the budget by hazard-weighted water-filling with a continuous speech-cost price. The audio-band budget B_ad = (20/ln10) pi^2 V / 2cS is set by the ratio of total cavity volume V to bore area S; occluding plugs are exempt. The f^2 price signal favours frequencies well above the source peak. Replacing strict transparency by a speech-cost price gives an exchange rate of about 1.3 dB of protection per decibel of speech cost under the present model, with the budget setting where it saturates. Across three form factors, low-frequency-selective designs stay near a decibel while hazard-matched mid/high-frequency designs reach twelve. The binding variables are bore area and speech allowance, not resonator count.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22395
PDF
-
Online Algorithms for Independent Low-Rank Matrix Analysis and Rank-Constrained Spatial Covariance Matrix Estimation Based on Maximum Weighted Likelihood Estimation
2026-09-18 01:02:59Yuto Ishikawa, Norihiro Takamune, Tomohiko Nakamura, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu KondoAbstract
Real-time multichannel speech extraction (MSE) under diffuse noise conditions is an important task with a wide range of applications, such as speech recognition and hearing aids. In this paper, we propose online algorithms for independent low-rank matrix analysis (ILRMA) and rank-constrained spatial covariance matrix estimation (RCSCME). Previously, we proposed a real-time extension of the RCSCME-based method: an MSE method based on ILRMA and RCSCME using the blockwise batch algorithm. However, it assumes that the spatial characteristics are stationary within a single batch, and thus, in dynamic situations where the target speaker moves, its performance may degrade. To address this problem, we derive the online algorithms for ILRMA and RCSCME in the following three steps. First, we formulate framewise cost functions for ILRMA and RCSCME on the basis of maximum weighted likelihood estimation. Second, we derive the update rules for the framewise cost functions on the basis of auxiliary-function techniques. These naive update rules are computationally costly for real-time execution on a practical machine. Thus, we finally derive the online algorithms by approximating some intermediate parameters with their estimates. Furthermore, we propose stabilization and further acceleration techniques for these online algorithms. In experiments, we simulate situations where a target speaker is stationary or moves and show that the proposed method achieves superior speech extraction performance compared with conventional methods. In addition, using real-world recorded signals, we demonstrate the effectiveness of the proposed method in practical scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21180
PDF
-
State-Space-Based FIR Filtering on a Quantum Computer
Abstract
Many signal processing tasks require intensive computations. Quantum computing promises to accelerate certain tasks, but algorithms must be designed around the limitations of quantum mechanics. This paper provides a quantum implementation of finite impulse response (FIR) filters, which are a widely used tool in classical signal processing. The filter can be parallelized and composed as part of larger quantum algorithms, with potential for speedups using quantum amplitude estimation and future fault-tolerant quantum hardware. To accomplish these properties, we introduce a state-space framework wherein sample-based signal processing is performed with unitary quantum circuits. We present the quantum delay gate as the quantum analog of the delay line in discrete-time signal processing. Unitary circuits intrinsically describe lossless systems, but we also implement lowpass and other bounded filters by emulating a projection operator. The FIR filter implementation is tested and demonstrated with a quantum circuit simulator.
Abstract (translated)
URL
https://arxiv.org/abs/2609.20331
PDF
-
CircleMatch: Prototype Matching with Circular Temporal Statistics for Tiny Keyword Spotting
Abstract
Keyword spotting (KWS), the task of identifying predefined words in speech, is a core capability of voice-enabled devices. Achieving high KWS accuracy under tight parameter budgets across different vocabulary sizes remains challenging. We present CircleMatch, a matching framework enabling KWS with very few parameters. Its encoder independently compresses frequency bands and fuses them into frame features. These features are then matched against learned class-specific prototypes to produce temporal response curves. Parameter-free circular aggregation encodes time as angles and summarizes response distributions and relative timing for classification. We develop four tiny variants, Circle-D4, Circle-D8, Circle-D16, and Circle-D32, ranging from approximately 1k to 7k parameters in the 12-class setting. Experiments with multiple random seeds on Speech Commands v1/v2 and the English and Spanish Micro subsets of the Multilingual Spoken Words Corpus demonstrate competitive accuracy with tiny models. Our qualitative analysis further suggests approximate shift equivariance of prototype responses and adaptation to temporal compression. Code and model weights are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.20070
PDF
-
Foreground Voice Activity Detection: Learning Speaker Selectivity from Supervision
2026-09-17 08:07:04Guangzhao Yang, Muhammad Huzaifah, Yu Pan, Jinya Sakurai, Ningjie BaiAbstract
Voice activity detection (VAD) fronts most voice-agent pipelines, yet production detectors treat all human speech, background talkers included, as valid activity; in crowded settings this floods recognition, stalls turn-taking, and triggers false barge-in. We formalize Foreground VAD (FVAD): a frame-synchronous, enrollment-free task in which only the dominant speaker, defined by sustained presence rather than instantaneous loudness, is positive, and which reduces to conventional VAD when a single speaker is present. We show that foreground selectivity is largely governed by training supervision: the crucial ingredient is an augmentation recipe pairing foreground-only labels with competing-speaker mixing, generated fully automatically without human annotation. To quantify selectivity we introduce the Background False-Alarm Rate (BG-FAR), gated by foreground F1, and build a controlled benchmark, Mix-Interference, complemented by an adapted VOiCES for real-world far-field evaluation. Across equal-size backbones, Mamba and LSTM perform on par while a longer-context attention model is no better, suggesting that training supervision plays a substantially larger role than temporal modeling capacity in achieving foreground selectivity. The resulting lightweight streaming model, Mamba-FVAD, outperforms commercial VADs and enrollment-based speaker-aware systems in foreground selectivity while staying competitive on conventional VAD, at 1-2 ms per-frame CPU latency.
Abstract (translated)
URL
https://arxiv.org/abs/2609.19856
PDF
