The reviewed record of science sign in
Pith

arxiv: 2606.31259 · v1 · pith:Y2ZK2JQV · submitted 2026-06-30 · cs.SD · cs.AI· cs.MM· eess.AS

SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation

Binh Mai , Tran Quoc Bao Le , Hung Dinh , Cong Tran This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel 2026-07-01 03:41 UTCgrok-4.3pith:Y2ZK2JQVrecord.jsonopen to challenge →

classification cs.SD cs.AIcs.MMeess.AS
keywords text-to-audiodiffusion distillationone-step generationvariational score distillationaudio generationcaption-only training
0
0 comments X

The pith

SwiftAudio distills a one-step text-to-audio model from a diffusion teacher using only text captions.

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

The paper demonstrates a method to train a fast, single-step text-to-audio generator by distilling from an existing multi-step diffusion model. It avoids the need for any paired text-audio examples and instead uses only text captions as supervision. The approach adapts variational score distillation to the audio setting and adds a regularization term that promotes smooth changes across time in the latent audio. With this setup the student model can be trained on roughly 45,000 captions and reaches the best reported results among strict one-step systems while reducing the performance gap to slower multi-step diffusion models.

Core claim

By adapting Variational Score Distillation to the audio domain and introducing a temporal smoothness regularization objective, the student model inherits the teacher's generative prior without requiring paired audio supervision and allows effective training with only approximately 45K captions.

What carries the argument

Adaptation of Variational Score Distillation to audio together with a temporal smoothness regularization objective that transfers the diffusion teacher's prior from captions alone.

If this is right

  • No paired audio data is required for training the one-step generator.
  • Inference requires only a single forward pass instead of iterative denoising steps.
  • State-of-the-art results are obtained among strict one-step methods on AudioCaps and Clotho.
  • Training succeeds with a modest set of approximately 45K text captions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same caption-only distillation pattern could be tested on text-to-video or text-to-image tasks.
  • Increasing the caption count beyond 45K might further reduce the remaining gap to multi-step systems.
  • Single-step generation would lower the compute needed for on-device or real-time audio synthesis.

Load-bearing premise

The combination of adapted variational score distillation and temporal smoothness regularization transfers the teacher's generative capability using only text captions.

What would settle it

Training the proposed student model on the 45K captions and measuring that its audio quality metrics on AudioCaps or Clotho remain below those of prior one-step baselines.

Figures

Figures reproduced from arXiv: 2606.31259 by Binh Mai, Cong Tran, Hung Dinh, Tran Quoc Bao Le.

Figure 1
Figure 1. Figure 1: Conceptual illustration of existing TTA paradigms with respect to [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of the proposed SwiftAudio framework. The student fθ is trained using the total joint loss Ltotal, integrating the VSD guidance (LVSD) from the teacher models and the temporal smoothness constraint (Ltemp) on the synthesized latents. The LoRA teacher ϵϕ is alternately updated via LLoRA to accurately estimate the student score. TABLE I COMPARISON OF REPRESENTATIVE ONE-STEP GENERATION FRAMEWORKS. T2… view at source ↗
Figure 3
Figure 3. Figure 3: Conceptual illustration of temporal regularization. Compared with VSD-only generation, adding temporal TV encourages a piecewise-smooth latent [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative results of the SwiftAudio framework. The figure illustrates [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Semantic Controllability and Latent Disentanglement in SwiftAudio. [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: The assessment interface for rating audio quality and relevance based [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Instruction page for participants, defining the rating criteria and [PITH_FULL_IMAGE:figures/full_fig_p011_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Visualizing semantic control via word swapping. SwiftAudio precisely modifies specific sound events and acoustic properties (e.g., source, environment, [PITH_FULL_IMAGE:figures/full_fig_p012_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Effect of attention reweighting. Increasing the weight of specific tokens enhances the intensity and presence of the target sound in the synthesized [PITH_FULL_IMAGE:figures/full_fig_p013_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Word refinement results in one-step text-to-audio generation. Starting from a base prompt (left), additional semantic phrases are appended (right), [PITH_FULL_IMAGE:figures/full_fig_p014_10.png] view at source ↗
read the original abstract

Diffusion-based text-to-audio (TTA) models achieve impressive synthesis quality but suffer from high inference latency due to iterative multi-step denoising. Existing one-step approaches alleviate this issue but still rely on paired text--audio data during distillation. To address these limitations, we propose SwiftAudio, a one-step TTA framework that performs audio-free distillation from a pretrained diffusion teacher using only text captions. Specifically, we adapt Variational Score Distillation (VSD) to the audio domain and introduce a temporal smoothness regularization objective to encourage coherent latent audio representations. This design enables the student model to inherit the teacher's generative prior without requiring paired audio supervision and allows effective training with only approximately 45K captions. Experiments on AudioCaps and Clotho demonstrate that SwiftAudio achieves state-of-the-art performance among strict one-step methods and substantially narrows the gap to multi-step diffusion systems. Project page: https://swiftaudio.org/

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper proposes SwiftAudio, a one-step text-to-audio (TTA) framework for caption-only distillation from a pretrained diffusion teacher. It adapts Variational Score Distillation (VSD) to the audio domain and introduces a temporal smoothness regularization objective, enabling training on ~45K captions without paired audio data. Experiments on AudioCaps and Clotho are claimed to show SOTA performance among strict one-step methods while narrowing the gap to multi-step diffusion systems.

Significance. If the experimental claims hold with proper validation, the work would advance data-efficient and low-latency TTA generation by removing the need for paired audio supervision during distillation. The caption-only setting and regularization approach address practical barriers in deploying diffusion-based audio models.

major comments (2)
  1. [Abstract] Abstract: the claim of achieving SOTA among one-step methods and substantially narrowing the gap to multi-step systems is asserted without any reported metrics, baselines, error bars, ablation studies, or quantitative results. This prevents verification of the central empirical claim.
  2. [Method] Method description: the adaptation of VSD to audio together with the temporal smoothness term is presented at a high level; without explicit loss equations or analysis showing that the student inherits the teacher's generative prior (rather than collapsing to a trivial or teacher-copying solution), it is unclear whether the approach is load-bearing for the no-paired-audio claim.
minor comments (1)
  1. [Abstract] The project page URL is given but the manuscript should be self-contained with at least a summary table of key metrics and comparisons.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive feedback. We address each major comment below and will incorporate revisions to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim of achieving SOTA among one-step methods and substantially narrowing the gap to multi-step systems is asserted without any reported metrics, baselines, error bars, ablation studies, or quantitative results. This prevents verification of the central empirical claim.

    Authors: We agree that the abstract would benefit from explicit quantitative support for its claims. In the revised version we will incorporate representative metrics from the experimental section (including comparisons to one-step and multi-step baselines on AudioCaps and Clotho) together with a brief mention of error bars and the scale of the caption-only training set. revision: yes

  2. Referee: [Method] Method description: the adaptation of VSD to audio together with the temporal smoothness term is presented at a high level; without explicit loss equations or analysis showing that the student inherits the teacher's generative prior (rather than collapsing to a trivial or teacher-copying solution), it is unclear whether the approach is load-bearing for the no-paired-audio claim.

    Authors: We acknowledge that the current method presentation remains high-level. We will expand Section 3 to include the full loss equations for the audio-adapted VSD objective and the temporal smoothness regularizer. We will also add a dedicated analysis subsection (with supporting ablations) that examines the student’s behavior under the caption-only regime and demonstrates that the combined objective prevents collapse to trivial or teacher-copying solutions while transferring the teacher’s generative prior. revision: yes

Circularity Check

0 steps flagged

No significant circularity; derivation relies on external VSD adaptation and empirical regularization

full rationale

The paper adapts Variational Score Distillation (VSD) to audio and adds a temporal smoothness term for caption-only training of a one-step student. No equations or derivation steps are shown that reduce a claimed prediction to a fitted input or self-citation by construction. The central claim (student inherits teacher prior via adapted losses on ~45K captions) is presented as an empirical outcome of the loss design rather than a definitional identity. No self-citation load-bearing, uniqueness theorem, or ansatz smuggling is referenced. This is the common case of a method paper whose validity rests on external benchmarks rather than internal tautology.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no explicit free parameters, axioms, or invented entities are described.

pith-pipeline@v0.9.1-grok · 5707 in / 1098 out tokens · 52447 ms · 2026-07-01T03:41:56.229051+00:00 · methodology

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

51 extracted references · 51 canonical work pages

  1. [1]

    Make-an-audio: Text-to-audio generation with prompt- enhanced diffusion models,

    R. Huang, J. Huang, D. Yang, Y . Ren, L. Liu, M. Li, Z. Ye, J. Liu, X. Yin, and Z. Zhao, “Make-an-audio: Text-to-audio generation with prompt- enhanced diffusion models,” inInternational Conference on Machine Learning (ICML), 2023, pp. 13 916–13 932

    work page 2023

  2. [2]

    Audiogen: Textually guided audio generation,

    F. Kreuk, G. Synnaeve, A. Polyak, U. Singer, A. D ´efossez, J. Copet, D. Parikh, Y . Taigman, and Y . Adi, “Audiogen: Textually guided audio generation,” inThe Eleventh International Conference on Learning Representations (ICLR), 2023

    work page 2023

  3. [3]

    AudioLDM: Text-to-audio generation with latent diffusion models,

    H. Liu, Z. Chen, Y . Yuan, X. Mei, X. Liu, D. Mandic, W. Wang, and M. D. Plumbley, “AudioLDM: Text-to-audio generation with latent diffusion models,” inProceedings of the 40th International Conference on Machine Learning (ICML), vol. 202, 2023, pp. 21 450–21 474

    work page 2023

  4. [4]

    Audioldm 2: Learning holistic audio generation with self-supervised pretraining,

    H. Liu, Y . Yuan, X. Liu, X. Mei, Q. Kong, Q. Tian, Y . Wang, W. Wang, Y . Wang, and M. D. Plumbley, “Audioldm 2: Learning holistic audio generation with self-supervised pretraining,”IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 2871–2883, 2024

    work page 2024

  5. [5]

    Any-to-any generation via composable diffusion,

    Z. Tang, Z. Yang, C. Zhu, M. Zeng, and M. Bansal, “Any-to-any generation via composable diffusion,”Advances in Neural Information Processing Systems, vol. 36, pp. 16 083–16 099, 2023

    work page 2023

  6. [6]

    Auffusion: Leveraging the power of diffusion and large language models for text-to-audio generation,

    J. Xue, Y . Deng, Y . Gao, and Y . Li, “Auffusion: Leveraging the power of diffusion and large language models for text-to-audio generation,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024

    work page 2024

  7. [7]

    Tango 2: Aligning diffusion-based text-to-audio generations through direct preference optimization,

    N. Majumder, C.-Y . Hung, D. Ghosal, W.-N. Hsu, R. Mihalcea, and S. Poria, “Tango 2: Aligning diffusion-based text-to-audio generations through direct preference optimization,” inProceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 564–572

    work page 2024

  8. [8]

    Denoising diffusion probabilistic models,

    J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” Advances in neural information processing systems, vol. 33, pp. 6840– 6851, 2020

    work page 2020

  9. [9]

    Denoising diffusion implicit models,

    J. Song, C. Meng, and S. Ermon, “Denoising diffusion implicit models,” inInternational Conference on Learning Representations (ICLR), 2021

    work page 2021

  10. [10]

    Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps,

    C. Lu, Y . Zhou, F. Bao, J. Chen, C. Li, and J. Zhu, “Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps,” inAdvances in Neural Information Processing Systems (NeurIPS), 2022

    work page 2022

  11. [11]

    Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models,

    ——, “Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models,”Machine Intelligence Research, pp. 1–22, 2025

    work page 2025

  12. [12]

    Elucidating the design space of diffusion-based generative models,

    T. Karras, M. Aittala, T. Aila, and S. Laine, “Elucidating the design space of diffusion-based generative models,” inAdvances in Neural Information Processing Systems (NeurIPS), 2022

    work page 2022

  13. [13]

    Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models,

    F. Bao, C. Li, J. Zhu, and B. Zhang, “Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models,” in International Conference on Learning Representations, 2021

    work page 2021

  14. [14]

    Consistency models,

    Y . Song, P. Dhariwal, M. Chen, and I. Sutskever, “Consistency models,” inProceedings of the International Conference on Machine Learning (ICML), 2023

    work page 2023

  15. [15]

    Consistencytta: Accelerating diffusion-based text-to-audio generation with consistency distillation,

    Y . Bai, T. Dang, D. Tran, K. Koishida, and S. Sojoudi, “Consistencytta: Accelerating diffusion-based text-to-audio generation with consistency distillation,” inINTERSPEECH, 2024

    work page 2024

  16. [16]

    Audiolcm: Efficient and high-quality text-to-audio generation with minimal inference steps,

    H. Liu, R. Huang, Y . Liu, H. Cao, J. Wang, X. Cheng, S. Zheng, and Z. Zhao, “Audiolcm: Efficient and high-quality text-to-audio generation with minimal inference steps,” inProceedings of the 32nd ACM Inter- national Conference on Multimedia, 2024, pp. 7008–7017

    work page 2024

  17. [17]

    Instructpix2pix: Learning to follow image editing instructions,

    T. Brooks, A. Holynski, and A. A. Efros, “Instructpix2pix: Learning to follow image editing instructions,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 18 392–18 402

    work page 2023

  18. [18]

    Ts2f: Text-assisted speech-to-face generation,

    B. D. Mai, H. M. Dinh, and C. Tran, “Ts2f: Text-assisted speech-to-face generation,”ICT Express, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S240595952500147X

    work page 2025

  19. [19]

    AudioCaps: Generating captions for audios in the wild,

    C. D. Kim, B. Kim, H. Lee, and G. Kim, “AudioCaps: Generating captions for audios in the wild,” inProceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, 2019, pp. 119–132

    work page 2019

  20. [20]

    WavCaps: A ChatGPT-assisted weakly-labelled audio captioning dataset for audio-language multimodal research,

    X. Mei, C. Meng, H. Liu, Q. Kong, T. Ko, C. Zhao, M. D. Plumbley, Y . Zou, and W. Wang, “WavCaps: A ChatGPT-assisted weakly-labelled audio captioning dataset for audio-language multimodal research,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, pp. 1–15, 2024

    work page 2024

  21. [21]

    Audiosetcaps: Enriched audio captioning dataset generation using large audio language models,

    J. BAI, H. Liu, M. Wang, D. Shi, W. Wang, M. D. Plumbley, W.-S. Gan, and J. Chen, “Audiosetcaps: Enriched audio captioning dataset generation using large audio language models,” inAudio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation, 2024. [Online]. Available: https://openreview.net/ forum?id=uez4PMZwzP

    work page 2024

  22. [22]

    Journeydb: A benchmark for generative image understanding,

    K. Sun, J. Pan, Y . Ge, H. Li, H. Duan, X. Wu, R. Zhang, A. Zhou, Z. Qin, Y . Wanget al., “Journeydb: A benchmark for generative image understanding,”Advances in neural information processing systems, vol. 36, pp. 49 659–49 678, 2023

    work page 2023

  23. [23]

    Laion- 5b: An open large-scale dataset for training next generation image-text models,

    C. Schuhmann, R. Beaumont, R. Vencu, C. Gordon, R. Wightman, M. Cherti, T. Coombes, A. Katta, C. Mullis, M. Wortsmanet al., “Laion- 5b: An open large-scale dataset for training next generation image-text models,”Advances in neural information processing systems, vol. 35, pp. 25 278–25 294, 2022

    work page 2022

  24. [24]

    Prolific- dreamer: High-fidelity and diverse text-to-3d generation with variational score distillation,

    Z. Wang, C. Lu, Y . Wang, F. Bao, C. Li, H. Su, and J. Zhu, “Prolific- dreamer: High-fidelity and diverse text-to-3d generation with variational score distillation,”Advances in neural information processing systems, vol. 36, pp. 8406–8441, 2023

    work page 2023

  25. [25]

    Swiftbrush: One-step text-to-image diffu- sion model with variational score distillation,

    T. H. Nguyen and A. Tran, “Swiftbrush: One-step text-to-image diffu- sion model with variational score distillation,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

    work page 2024

  26. [26]

    Swiftbrush v2: Make your one-step diffusion model better than its teacher,

    T. Dao, T. H. Nguyen, T. Le, D. Vu, K. Nguyen, C. Pham, and A. Tran, “Swiftbrush v2: Make your one-step diffusion model better than its teacher,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 176–192

    work page 2024

  27. [27]

    Clotho: An audio captioning dataset,

    K. Drossos, S. Lipping, and T. Virtanen, “Clotho: An audio captioning dataset,” inICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020, pp. 736–740

    work page 2020

  28. [28]

    Audiolm: A lan- guage modeling approach to audio generation,

    Z. Borsos, N. Chen, A. Roberts, M. Tagliasacchiet al., “Audiolm: A lan- guage modeling approach to audio generation,”IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 2523–2533, 2023

    work page 2023

  29. [29]

    Diffsound: Discrete diffusion model for text-to-sound generation,

    D. Yang, J. Yu, H. Wang, W. Wang, C. Weng, Y . Zou, and D. Yu, “Diffsound: Discrete diffusion model for text-to-sound generation,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 1720–1733, 2023

    work page 2023

  30. [30]

    Improved techniques for training score- based generative models,

    T. Karras, S. Laine, and T. Aila, “Improved techniques for training score- based generative models,”Advances in Neural Information Processing Systems, vol. 33, pp. 2651–2662, 2020

    work page 2020

  31. [31]

    Text-to-audio gen- eration using instruction guided latent diffusion model,

    D. Ghosal, N. Majumder, A. Mehrish, and S. Poria, “Text-to-audio gen- eration using instruction guided latent diffusion model,” inProceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada. ACM, 2023, pp. 3590–3598. 10

    work page 2023

  32. [32]

    Diffwave: A versatile diffusion model for audio synthesis,

    Z. Kong, W. Ping, J. Huang, K. Zhao, and B. Catanzaro, “Diffwave: A versatile diffusion model for audio synthesis,” inInternational Confer- ence on Learning Representations (ICLR), 2021

    work page 2021

  33. [33]

    Wave- grad: Estimating gradients for waveform generation,

    N. Chen, Y . Zhang, H. Zen, R. Weiss, M. Norouzi, and W. Chan, “Wave- grad: Estimating gradients for waveform generation,” inInternational Conference on Learning Representations (ICLR), 2021

    work page 2021

  34. [34]

    High- resolution image synthesis with latent diffusion models,

    R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer, “High- resolution image synthesis with latent diffusion models,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogni- tion (CVPR), 2022, pp. 10 684–10 695

    work page 2022

  35. [35]

    Pseudo numerical methods for diffusion models on manifolds,

    L. Liu, Y . Ren, Z. Lin, and Z. Zhao, “Pseudo numerical methods for diffusion models on manifolds,” inInternational Conference on Learning Representations, 2022

    work page 2022

  36. [36]

    Progressive distillation for fast sampling of diffusion models,

    T. Salimans and J. Ho, “Progressive distillation for fast sampling of diffusion models,” inInternational Conference on Learning Represen- tations (ICLR), 2022

    work page 2022

  37. [37]

    Dreamfusion: Text-to-3d using 2d diffusion,

    B. Poole, A. Jain, J. T. Barron, and B. Mildenhall, “Dreamfusion: Text-to-3d using 2d diffusion,” inInternational Conference on Learning Representations (ICLR), 2023

    work page 2023

  38. [38]

    Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation,

    H. Wang, X. Du, J. Li, R. A. Yeh, and G. Shakhnarovich, “Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 12 619–12 629

    work page 2023

  39. [39]

    Magic3d: High-resolution text-to- 3d content creation,

    C.-H. Lin, J. Gao, L. Tang, T. Takikawa, X. Zeng, X. Huang, K. Kreis, S. Fidler, M.-Y . Liu, and T.-Y . Lin, “Magic3d: High-resolution text-to- 3d content creation,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2023, pp. 300– 309

    work page 2023

  40. [40]

    Latent-nerf for shape-guided generation of 3d shapes and textures,

    G. Metzer, E. Richardson, O. Patashnik, R. Giryes, and D. Cohen-Or, “Latent-nerf for shape-guided generation of 3d shapes and textures,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2023, pp. 12 663–12 673

    work page 2023

  41. [41]

    Fantasia3d: Disentangling geometry and appearance for high-quality text-to-3d content creation,

    R. Chen, Y . Chen, N. Jiao, and K. Jia, “Fantasia3d: Disentangling geometry and appearance for high-quality text-to-3d content creation,” in IEEE/CVF International Conference on Computer Vision, ICCV. IEEE, 2023, pp. 22 189–22 199

    work page 2023

  42. [42]

    LoRA: Low-rank adaptation of large language models,

    E. J. Hu, yelong shen, P. Wallis, Z. Allen-Zhu, Y . Li, S. Wang, L. Wang, and W. Chen, “LoRA: Low-rank adaptation of large language models,” inInternational Conference on Learning Representations (ICLR), 2022

    work page 2022

  43. [43]

    Nonlinear total variation based noise removal algorithms,

    L. I. Rudin, S. Osher, and E. Fatemi, “Nonlinear total variation based noise removal algorithms,”Physica D: nonlinear phenomena, vol. 60, no. 1-4, pp. 259–268, 1992

    work page 1992

  44. [44]

    A duality based approach for realtime tv-l 1 optical flow,

    C. Zach, T. Pock, and H. Bischof, “A duality based approach for realtime tv-l 1 optical flow,” inJoint pattern recognition symposium. Springer, 2007, pp. 214–223

    work page 2007

  45. [45]

    Classifier-free diffusion guidance,

    J. Ho and T. Salimans, “Classifier-free diffusion guidance,” inNeurIPS 2021 Workshop on Deep Generative Models and Downstream Applica- tions, 2021

    work page 2021

  46. [46]

    Decoupled weight decay regularization,

    I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” inInternational Conference on Learning Representations

    work page

  47. [47]

    Panns: Large-scale pretrained audio neural networks for audio pattern recognition,

    Q. Kong, Y . Cao, T. Iqbal, Y . Wang, W. Wang, and M. D. Plumbley, “Panns: Large-scale pretrained audio neural networks for audio pattern recognition,”IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp. 2880–2894, 2020

    work page 2020

  48. [48]

    Cnn architectures for large-scale audio classification,

    S. Hershey, S. Chaudhuri, D. P. Ellis, J. F. Gemmeke, A. Jansen, R. C. Moore, M. Plakal, D. Platt, R. A. Saurous, B. Seyboldet al., “Cnn architectures for large-scale audio classification,” in2017 ieee international conference on acoustics, speech and signal processing (icassp). IEEE, 2017, pp. 131–135

    work page 2017

  49. [49]

    Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation,

    Y . Wu*, K. Chen*, T. Zhang*, Y . Hui*, T. Berg-Kirkpatrick, and S. Dub- nov, “Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation,” inIEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2023

    work page 2023

  50. [50]

    Supercharged one-step text-to-image diffusion models with negative prompts,

    V . Nguyen, A. Nguyen, T. Dao, K. Nguyen, C. Pham, T. Tran, and A. Tran, “Supercharged one-step text-to-image diffusion models with negative prompts,” inProceedings of the IEEE/CVF International Con- ference on Computer Vision (ICCV), October 2025, pp. 18 004–18 013

    work page 2025

  51. [51]

    Prompt-to-prompt image editing with cross-attention control,

    A. Hertz, R. Mokady, J. Tenenbaum, K. Aberman, Y . Pritch, and D. Cohen-Or, “Prompt-to-prompt image editing with cross-attention control,” inThe Eleventh International Conference on Learning Rep- resentations, 2023. VII. BIOGRAPHYSECTION Binh Maireceived an Engineering degree with Hon- ors in Information Technology from the Posts and Telecommunications In...

    work page 2023