arXiv_SD
-
DEFINE: Exemplar-Guided Accent Control for Zero-Shot TTS
2026-09-30 22:28:05Ambuj Mehrish, Abhinaba Roy, Alex Ivanov, Tawsif Ahmed, Dorien HerremansAbstract
Zero-shot text-to-speech (TTS) can reproduce an unseen speaker from a short reference recording, but typically entangles speaker identity and accent within the same reference. We introduce DEFINE, an end-to-end framework that decouples these factors by conditioning speaker identity and target accent on separate audio exemplars. A single inference-time guidance weight continuously controls accent strength without retraining. Built on F5-TTS with parameter-efficient LoRA adaptation, DEFINE maps short accent exemplars into a conditioning space using an exemplar encoder supervised through learned accent prototypes, requiring neither accent labels at inference time nor post-synthesis waveform conversion. On seen accents, increasing accent guidance improves accent-probe accuracy from 6.5% to 19.6%. More importantly, a single DEFINE model generalizes accent control beyond its training accent set: on seen and out-of-domain accents, though not on held-out accents, it matches the accent transfer performance of a two-model TTS-voice-conversion cascade while achieving higher speaker similarity and comparable predicted speech quality. These results demonstrate that speaker identity and accent can be independently controlled from audio exemplars within a single zero-shot TTS model, including for accents unseen during training.
Abstract (translated)
URL
https://arxiv.org/abs/2609.32777
PDF
-
MAV-C: A Framework for the Joint Objective Estimation of Audio-Visual Complexity in Immersive Virtual Environments
2026-09-30 21:47:48Luca Resti, Amelia Gully, Michael McLoughlin, Gavin Kearney, Alena DenisovaAbstract
We present the Motion-Aware Audio-Visual Complexity Metric (MAV-C), a reference-free framework for the joint objective estimation of audio-visual complexity. The metric combines entropy-based audio features (temporal, spectral, and spatial) with visual features (Sobel gradient magnitude, chromatic uniqueness, and optical flow) via a parametric fusion stage, producing a continuous joint complexity score CAV (t) [0,1]. We validate MAV-C on two datasets: a controlled synthetic corpus (SYN) of stimuli with known signal characteristics and a naturalistic gameplay corpus (GAM) of 60 clips drawn from the SAFEPLAY-X dataset. On SYN, the metric exhibits strong validity: the audio score CA and visual score CV are each insensitive to changes in the opposite modality (CoV < 0.003), the joint score CAV spans [0.00,0.90] across all parameter combinations, and single-axis feature sweeps produce monotone trajectories (Spearman up to 0.995). On GAM, CV differs significantly across content categories (Kruskal-Wallis p = 0.021) while CA does not, and the two sub-scores are uncorrelated (r = 0.03), confirming they operate on independent signal dimensions. OFAT sensitivity analysis identifies a two-tier parameter hierarchy, with modality balance (wa) and visual regularization (v) as most significant tunable parameters. Full subjective calibration is planned as future work.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00754
PDF
-
Where the Body Keeps the Beat: Structured Motion Conditioning and Music Dynamics Supervision for Dance-to-Music Generation
Abstract
Dance-to-music (D2M) generation aims to synthesize musically plausible soundtracks whose temporal structure aligns with a given dance performance. Representative D2M methods do not explicitly distinguish motion cues across body parts and frequency bands, while standard flow matching lacks a dedicated objective for supervising local music-latent dynamics. To address these issues, we propose Dyna2Music, a latent flow-matching framework that combines structured motion conditioning with explicit supervision of music-latent dynamics. An empirical analysis on AIST++ quantifies how spatial partitioning and frequency separation affect raw music-to-kinematic beat alignment and motion-reference density, informing the conditioning design. Accordingly, Dyna2Music decomposes joint velocities into slow and fast components and hierarchically fuses the resulting part-wise motion energy with pretrained joint features to condition music generation. To complement this representation, we introduce latent dynamics consistency (LDC), an auxiliary objective that matches adjacent-frame change magnitudes between a single-step clean-latent estimate and the paired reference. LDC makes local music-latent variation an explicit training target without adding trainable parameters or inference computation. Dyna2Music supports variable-length music generation, and experiments on AIST++ and TikTok demonstrate improved rhythmic alignment and audio quality over representative D2M baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00726
PDF
-
AnchorPrompt: Self-Distilled Soft Prompts for Robust Audio-Language Models
2026-09-30 20:53:46Pooneh Mousavi, Amir Ivry, Mirco Ravanelli, Cem SubakanAbstract
Large audio-language models (LALMs) are sensitive to input perturbations, such as noise, waveform corruption, and adversarial injections. We propose AnchorPrompt, an efficient adaptation method that keeps the model frozen and learns a single block of prompt vectors inserted at the decoder input, between the audio and question embeddings. We train these vectors through self-distillation over diverse audio and text perturbations. To improve answer consistency and mitigate hallucination, we use the model's prediction on the clean recording as the target for answerable inputs, and assign a refusal target when the audio lacks sufficient evidence to answer. Furthermore, AnchorPrompt is perturbation-agnostic at inference, requiring no prior detection of perturbations and enabling zero-shot transfer to unseen distortions. We evaluate three LALMs across three benchmarks and show that AnchorPrompt improves answer consistency in most tested conditions. Clean accuracy improves in six of nine model-benchmark pairs, with minimal impact on the remainder of 1.2% at most. Crucially, AnchorPrompt reduces hallucinations under severe audio corruption while keeping false refusals on clean audio rare. Finally, these consistency gains transfer to unseen perturbations, such as choice permutations and reverberation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00706
PDF
-
Balalaika-Longform: A Russian Speech Corpus for Continuous Long-Form Text-to-Speech
2026-09-30 19:58:11Nikita Vasiliev, Kirill Borodin, Vasilii Kudryavtsev, Maxim Maslov, Grach MkrtchianAbstract
Long-form text-to-speech must retain requested words over extended generations, yet sentence-level training and evaluation can hide omissions and early stops. We introduce Balalaika-Longform, an open Russian corpus of 189 hours in continuous units of 30 seconds to 15 minutes. Long units and matched short windows support fine-tuning comparisons on the same source recordings, and the accompanying evaluation retains every synthesis attempt. We fine-tune CosyVoice3, Qwen3-TTS, VoxCPM2 and F5-TTS on either view and test continuous synthesis on 50 text-voice pairs with voices unseen in fine-tuning, at about 75, 300 and 1,200 words. At 1,200 words, CosyVoice3 WER falls from 99.9% after short-window fine-tuning to 47.3% with long targets, and to 16.6% with punctuated, format-matched transcripts; paired intervals favor long targets for Qwen3-TTS and VoxCPM2, and by a small margin for F5-TTS, whose absolute WER stays above 90%. The results isolate the effect of training sequence length under a fixed continuous-generation protocol.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00658
PDF
-
On Evaluating Quantum Kernel Robustness for Low-Resource Cross-Corpus Audio Deepfake Detection
2026-09-30 19:51:25Lisan Al Amin, Lei Zhang, Vandana P. JanejaAbstract
Synthetic speech detection is critical for audio security, but performance can degrade when labeled data are scarce and evaluation conditions differ from training. This study examines quantum kernel methods and lightweight neural models for cross-corpus audio deepfake detection under limited training data. We compare a Quantum Support Vector Machine (QSVM), a classical support vector machine (SVM), and a multilayer perceptron (MLP), all trained on frozen wav2vec 2.0 embeddings using a strict budget of 200 training samples. To match the qubit budget of near-term quantum hardware, embeddings are reduced to four dimensions using principal component analysis, and all models use the same reduced features. Experiments on ASVspoof 2019, ASVspoof 5, the ADD 2023 Challenge, and the In-the-Wild dataset show that under severe domain shift from ASVspoof 2019 to ADD 2023, the MLP degrades to near-random performance, with an area under the curve of approximately 50% and an equal error rate of 50.0%. In contrast, the QSVM maintains meaningful discrimination, achieving an area under the curve of 76.0% and an equal error rate of 27.0%. This advantage is not consistent across transfer directions. When trained on ADD 2023, the QSVM falls below chance on two of three transfers, while the MLP performs better. These results suggest that quantum kernel methods can be competitive under severe cross-corpus shifts and strict low-resource constraints, but do not provide a consistent advantage under near-domain transfer. We interpret these findings as an empirical characterization of quantum kernel inductive bias under distribution shift, rather than evidence of quantum advantage, since the four-qubit kernel can be simulated exactly on classical hardware.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00649
PDF
-
PLACE: Positional Latent Adaptation via Conditioned Embeddings for Binaural Audio Generation
2026-09-30 19:33:01Tiernon Riesenmy, You Zhang, Gautam Bhattacharya, Andrea FanelliAbstract
We present PLACE, a method that extends the pretrained any-to-audio model AudioX for binaural generation from arbitrary combinations of text, video, and optional audio prompts. PLACE augments video conditioning with Perception Encoder Core features, aligns text and video representations to derive spatial cues, and applies a conditioning-dependent low-rank transformation to the generated latent. The adapter is supervised via decoded-audio interaural level and time difference objectives. Trained on MRSAudio, PLACE improves most metrics over ViSAGe on FAIR-Play and achieves an improved SpatialCLAP score over SpatialSonic on the BEWO-1M Single Static test split. Listener evaluations favor PLACE for video-to-audio and out-of-distribution text-to-audio generation, demonstrating flexible multimodal control and improved spatial consistency.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00630
PDF
-
End-to-End Historical Music Restoration in Latent Space
2026-09-30 19:11:36Steven Cho, Junghyun Koo, Raphael Lafargue, Tushar Dhyani, Eloi Moliner, Yuki MitsufujiAbstract
Historical music restoration (HMR) has almost exclusively focused on constrained problems such as Super-Resolution or the restoration of solo pieces, under-exploring the general task of restoring orchestral historical music, which has multiple instruments. This under-exploration is largely because the HMR domain, early-20th-century recordings, has no pre-degradation ground-truth pairs, making the restoration task unsupervised and more challenging. This paper presents a supervised end-to-end orchestral HMR benchmark by exploring both the synthetic degradation functions and the end-to-end generative deep-learning restoration methods. We simulate the historical recording degradation chain more faithfully than prior work, which makes orchestral restoration into a tractable supervised problem. A latent flow-matching model trained on the resulting synthetic pairs outperforms existing HMR baselines on intrusive, non-intrusive, and subjective evaluations. We also curate and release a 9.3-hour license-free, unpaired, historical classical-music test set, along with code and audio demos.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00607
PDF
-
Collapse, Not Invariance: Diagnosing Auxiliary Objectives in Speech Anti-Spoofing
2026-09-30 18:21:29Ksenia Lysikova, Kirill Borodin, Maxim Maslov, Grach MkrtchianAbstract
Speech anti-spoofing countermeasures degrade when the generator, codec or channel changes, and a common remedy is an auxiliary objective that shapes the embedding space; whether it does is invisible to EER, a pure ranking metric. We compare seven such objectives with cross-entropy over 113 runs on five corpora, AASIST3 at three seeds plus four pre-trained detectors, and measure the embedding space of the 24 AASIST3 runs directly. Raw augmentation displacement makes cosine consistency look effective, but the gain is a smaller space, not a more stable one: normalised by the spread, no configuration consistently improves on cross-entropy. Every trained space is dominated by the single decision axis expected for two classes, whose training-set structure does not transfer, and four runs collapse to a near-constant output that displacement rewards and EER reports as poor accuracy. No auxiliary objective keeps an advantage over cross-entropy across architectures, corpora and seeds.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00539
PDF
-
ProxyMOS: Label-Free Speech Quality Assessment by Multi-Teacher Distillation with Adaptive Routing
2026-09-30 14:57:17Maxim Trokunov, Kirill Borodin, Nikita Vasiliev, Grach MkrtchianAbstract
Human mean opinion scores (MOS) are costly to collect, and non-intrusive MOS predictors degrade sharply outside their training domain. ProxyMOS turns a pool of public MOS predictors into a single stronger model without new human labels. Eight predictors are benchmarked against human ratings; the five most informative enter a subset search under uniform, correlation-weighted, error-weighted, MSE-optimised and adaptive per-utterance routing; and the best routed four-model ensemble labels 807k unlabeled utterances that train a wav2vec 2.0 student. On URGENT the student reaches Spearman $\rho=0.802$ against $0.773$ for the best teacher. On mos260, a new Russian TTS benchmark of 4,600 utterances from 38 synthesis conditions, it reaches $\rho=0.636$ against $0.613$ per utterance and $0.95$ per condition, matching its own routed ensemble in one forward pass. Adaptive routing is the only rule that does not degrade when weak predictors are added. Model, ONNX exports and mos260 are released. It's about 950 characters; arXiv's limit is 1,920. I kept $\rho$ because arXiv renders it on the abstract page. If you'd rather avoid math, replace $\rho=0.802$ with rho = 0.802 and do the same for the other $...$ values.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00419
PDF
-
Pitch Smoothing Using Relative Interval Networks
2026-09-30 14:42:03Chin-Yun Yu, Chi-Jen Peng, Li Su, Gy\"orgy FazekasAbstract
Pitch tracking systems typically couple a per-frame fundamental frequency ($F_0$) estimator with a temporal smoothing stage to obtain continuous trajectories. Conventional Viterbi smoothers enforce first-order continuity but lack long-term temporal awareness and could lock into octave errors across corrupted frames. We propose Relative Interval Networks (RIN), a trajectory smoothing framework that reconciles per-frame pitch estimates with data-driven multi-hop pitch differences. We extract robust relative pitch intervals across arbitrary frame offsets using Variable-Q Transform cross-correlation. We formulate pitch smoothing as an $L_1$-norm optimization problem and prove its equivalence to a minimum cost circulation problem, solved efficiently via linear programming. Evaluations across speech, singing, and instrumental datasets show that RIN substantially improves weak estimators, matches or outperforms Viterbi decoding at a comparable computational cost, and provides superior robustness under certain acoustic degradation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39852
PDF
-
SEAR: Spoofing Evidence-Grounded Audio Reasoning Benchmark for Audio Language Models
2026-09-30 14:39:47Rong Wan, Suliu Qin, Jiaxi Li, Wei Xie, Wenwu Wang, Xiaolong Han, Lu Yin, Xilu WangAbstract
Audio language models (ALMs) are increasingly used for audio deepfake detection (ADD), yet existing benchmarks assess their verdicts or rationale plausibility without verifying the underlying acoustic evidence. To address this issue, we first introduce spoofing evidence-grounded audio reasoning (SEAR), a four-task AQA benchmark to evaluate ALM-based ADD through acoustic evidence identification and quantification, deepfake detection, and forensic rationale generation. We further propose a bona-fide-based acoustic evidence agent (BAEA), which equips a frozen ALM with controlled acoustic tools under \textsc{fixed} or \textsc{adaptive} evidence-acquisition policies. Experiments with six ALMs reveal a clear gap between plausible rationales and verifiable acoustic evidence reasoning, while BAEA-\textsc{Fixed} improves final verdicts and forensic rationales on both evaluation partitions. Controlled interventions further show that misleading evidence degrades both detection and grounding performance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39847
PDF
-
Synthetic Speech Attribution via Prototypical Networks
2026-09-30 13:33:49Viola Negroni, Paolo Bestagini, Stefano TubaroAbstract
Synthetic speech attribution aims to identify the generative system responsible for a speech signal, but current approaches typically rely on black-box neural networks that provide limited insight into their decisions. This work investigates prototype-based networks as an interpretable alternative, where predictions are grounded in comparisons with representative training examples. We adapt ProtoPNet to spectrogram-based speech representations and evaluate the proposed framework on the MLAAD dataset under closed-set, cross-lingual, and open-set conditions. Experiments show that prototype-based reasoning achieves competitive or improved attribution performance compared with the baseline while enabling example-based explanations. These results highlight that interpretability and performance can be jointly achieved in synthetic speech attribution through prototype-based modeling.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39722
PDF
-
SE-ADD: Self-Evolving Audio Deepfake Detection with Mistake-Driven Supervision
2026-09-30 13:10:57Rong Wan, Wei Xie, Jiaxi Li, Wenwu Wang, Lu Yin, Yiliao Song, Xilu WangAbstract
Audio deepfake detection (ADD) must remain effective when new spoofing attacks emerge after deployment. Emerging audio language model (ALM)-based ADD methods are built on predefined supervision from ground-truth labels or verified forensic rationales. However, this paradigm overlooks an ALM's own mistakes, which indicate where targeted supervision is most needed. To this end, we first introduce evolving spoofing environments for ALM-based ADD, where a new attack becomes dominant while previously observed attacks persist. Motivated by the above learning-from-mistakes perspective, we further propose SE-ADD, a self-evolving framework that iteratively adapts an ALM via low-rank adaptation (LoRA) using mistake-driven supervision built from its verdicts and self-generated forensic cues. All training samples receive direct authenticity supervision, while misclassified ones receive additional cue-augmented supervision. As verdicts and cues are regenerated by the updated ALM, the resulting supervision evolves accordingly. Experiments on two ALMs demonstrate the effectiveness of SE-ADD in generalizing to unseen attacks, reducing the equal error rate (EER) from $36.72\%$ to $7.52\%$ for Qwen2-Audio and from $19.93\%$ to $3.97\%$ for MOSS-Audio.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39679
PDF
-
Neural Audio Codec for Robust Audio Deepfake Detection
2026-09-30 12:53:53Jungwoo Kim, Joonyong Park, Junyoung Koh, Jong-Seok LeeAbstract
Audio deepfake detectors are typically evaluated on uncompressed audio, although real-world audio often undergoes low-bitrate coding. In this work, we investigate how audio coding affects deepfake detection across codecs, bitrates, and detectors, finding higher errors at lower rates. A mixed-pair protocol isolates codec-induced changes in bona fide and spoof audio, revealing asymmetric, codec-dependent failures: low-rate DAC and EnCodec mainly degrade bona fide detection, whereas X-Codec shows a stronger spoof-side limitation. Motivated by these, we propose a forensic-preserving neural audio codec (FP-NAC), which fine-tunes a pretrained codec using a detector-guided objective while preserving its native hard quantization path and bitrate. On ASVspoof 2019 LA, FP-NAC reduces EER by up to 49.8~pp compared with the original DAC at 0.5~kbps while maintaining comparable reconstruction quality. Although supervised by only one detector, FP-NAC improves performance across multiple detectors, highlighting forensic transparency as a codec design objective alongside perceptual quality. Our codes are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39651
PDF
-
Ghost in the Encoder: Decodable Artist Identity Representations in Lyrics-to-Song Generation
2026-09-30 11:51:21Arhan Vohra, Choenden Kyirong, Laura Ib\'a\~nez-Mart\'inez, Mart\'in RocamoraAbstract
Text-to-song generation models can be prompted to imitate specific artists or regurgitate entire songs from their training data. Although these phenomena have been documented behaviorally on small datasets, little is known about the internal representations that may give rise to them. Prior interpretability work on generative audio has focused on locating semantic concepts such as genre or time signature within model activations. In this work, we show that a trained model can be probed for linearly decodable representations of artist identity from song lyrics alone, without any additional identifiers. Through a controlled case study of ACE-Step 1.5 spanning 2,000 songs across 100 artists, we demonstrate that the artist associated with a given set of lyrics can be identified within the model's internal activations, and that this conditioning signal propagates from the lyric encoder to the diffusion backbone during inference. These findings indicate that lyrics constitute an artist-level conditioning channel not addressed by prompt-side replication safeguards. More broadly, our work highlights how latent-space analysis can be used to audit what generative music models have implicitly learned from their training data.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39552
PDF
-
Harmonizing Spectral Evolution in Conditional Flow Matching for TTS
2026-09-30 07:55:59Isha Pandey, Varad Deshpande, Abhijat Bharadwaj, Ganesh RamakrishnanAbstract
Conditional Flow Matching (CFM) models for text-to-speech (TTS) suffer from incoherent frequency evolution during inference. While similar spectral imbalances are addressed in diffusion models for other domains, those generic solutions fail to generalize to the inherently uncoordinated acoustic dynamics of CFM. We demonstrate that this issue can be effectively mitigated by introducing a novel training-free frequency-selective boosting strategy. Using the Discrete Wavelet Transform (DWT), our method dynamically modulates mel-spectrogram sub-bands during ODE integration, synchronizing spectral development by penalizing aggressive low-frequency growth and boosting lagging high-frequency details. Validated across diverse architectures (Matcha-TTS, F5-TTS, IndicF5), our approach reduces the required Number of Function Evaluations (NFE) from 32 to 26 and improves Frechet Audio Distance (FAD) by up to 61%, all without compromising mean opinion scores, speaker similarity, and speech intelligibility.
Abstract (translated)
URL
https://arxiv.org/abs/2609.34431
PDF
-
Training-Free Affinity Fusion of Neural and Embedding-Based Speaker Diarization
Abstract
Speaker diarization systems based on speaker embeddings and neural diarization exploit complementary forms of speaker information, but their intermediate representations are not directly compatible. We introduce Training-Free Affinity Fusion (TFAF), which integrates the speaker structure inferred by a neural diarizer into an embedding-based diarization system. The neural speaker partition is used to condition local speaker representations, from which we construct a continuous affinity matrix and combine it with the embedding-based acoustic affinity before a single global clustering step. The method requires no additional training, shared embedding space, speaker-label alignment, or hard transfer of the neural diarizer's speaker count. Experiments on AMI and CALLHOME show consistent DER improvements over both constituent systems; on AMI, fusion also improves speaker-attributed transcription. Ablations show that the neural speaker partition accounts for most of the gain, while retaining the continuous embedding-based affinities provides additional benefit over hard partition fusion.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39162
PDF
-
Game Sound-Effect Completion with Event-Level Transformation Hints
Abstract
Creating sound effects for a new game-character skin requires a distinct acoustic identity while preserving gameplay-event roles. The challenge is to complete a coherent set of related sounds whose required degrees of redesign differ. We formulate this task as completion conditioned on base-skin audio, completed target assets, and a textual design description. We develop a pipeline to collect, process, and align corresponding events across League of Legends skins. Building on Stable Audio 3's pretrained audio prior, we fine-tune a latent inpainting model to jointly complete missing events. A signed soft retention mask encodes available audio and an adjustable transformation hint for each missing event, specifying the requested balance between retention and redesign. Experiments on held-out skins show improved reconstruction over the evaluated general-purpose audio editors. Target-derived hints further improve paired similarity, with three-level hints retaining most of the benefit of continuous guidance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39044
PDF
-
How Reliable Are Predicted MOS for Reproducing Human System-Level Preferences in Speech Enhancement?
2026-09-30 05:35:30Nahomi Kusunoki, Tsubasa Ochiai, Naohiro Tawara, Marc Delcroix, Naoyuki Kamo, Tetsuji Ogawa, Shoko ArakiAbstract
We investigate whether predicted Mean Opinion Scores (MOS) can reliably support system-level comparisons of speech enhancement (SE) methods by introducing system-level preference accuracy (SPA). Although MOS prediction models are widely used to evaluate SE systems, their performance is typically assessed by correlation with human-rated MOS, which does not guarantee agreement on which system is better. SPA addresses this gap by directly evaluating whether predicted and human-rated MOS yield the same system preferences. Using SPA, we systematically evaluate three settings: single prediction models, ensembling, and domain adaptation. Through experiments, SPA varies substantially across single prediction models, from 9.4% to 76.8%. Even the best model disagrees with human judgments in approximately 23% of system comparisons. Ensembling yields only limited improvement, while domain adaptation tends to substantially improve SPA in the closed condition but brings only modest gains in the more practical open condition, where neither the target systems nor the speakers are known. These results suggest that SPA can reveal errors correlation-based evaluation alone does not expose, and that predicted MOS alone can lead to unreliable conclusions in practical SE system comparison.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39032
PDF
