Chieh-Hsin Lai

Identifiers

• name variant Chieh-Hsin Lai 0.60 · backfill

Papers (39)

1. Understanding and Accelerating the Training of Masked Diffusion Language Models cs.LG · 2026 · author #3
2. A Unified View of Score-Based and Drifting Models cs.LG · 2026 · author #1
3. Noise Scheduling as Information-Guided Allocation in Diffusion Training cs.LG · 2026 · author #7
4. Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training cs.LG · 2026 · author #5
5. GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning cs.LG · 2026 · author #3
6. TINNs: Time-Induced Neural Networks for Solving Time-Dependent PDEs cs.LG · 2026 · author #5
7. The Principles of Diffusion Models cs.LG · 2025 · author #1
8. Denoising Multi-Beta VAE: Representation Learning for Disentanglement and Generation cs.LG · 2025 · author #3
9. VCT: Training Consistency Models with Variational Noise Coupling cs.LG · 2025 · author #3
10. Consistency Training with Physical Constraints cs.LG · 2025 · author #5
11. Music Foundation Model as Generic Booster for Music Downstream Tasks cs.SD · 2024 · author #5
12. Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion cs.LG · 2024 · author #2
13. $\textit{Jump Your Steps}$: Optimizing Sampling Schedule of Discrete Diffusion Models cs.LG · 2024 · author #2
14. HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning cs.LG · 2024 · author #3
15. Bellman Diffusion: Generative Modeling as Learning a Linear Operator in the Distribution Space cs.LG · 2024 · author #2
16. A Survey on Diffusion Models for Inverse Problems cs.LG · 2024 · author #3
17. Latent Diffusion Bridges for Unsupervised Musical Audio Timbre Transfer cs.SD · 2024 · author #5
18. DisMix: Disentangling Mixtures of Musical Instruments for Source-level Pitch and Timbre Manipulation cs.SD · 2024 · author #7
19. SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation cs.SD · 2024 · author #4
20. GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping cs.CV · 2024 · author #7
21. PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher cs.CV · 2024 · author #2
22. Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric cs.LG · 2024 · author #4
23. HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes cs.LG · 2023 · author #6
24. Manifold Preserving Guided Diffusion cs.LG · 2023 · author #3
25. On the Language Encoder of Contrastive Cross-modal Models cs.CL · 2023 · author #4
26. Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion cs.LG · 2023 · author #2
27. VRDMG: Vocal Restoration via Diffusion Posterior Sampling with Multiple Guidance eess.AS · 2023 · author #4
28. The Sound Demixing Challenge 2023 $\unicode{x2013}$ Music Demixing Track eess.AS · 2023 · author #3
29. On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization cs.LG · 2023 · author #1
30. SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer cs.LG · 2023 · author #4
31. GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration cs.LG · 2023 · author #3
32. Unsupervised vocal dereverberation with diffusion-based generative models eess.AS · 2022 · author #4
33. FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation cs.LG · 2022 · author #1
34. SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization cs.LG · 2022 · author #4
35. Robust Vector Quantized-Variational Autoencoder cs.LG · 2022 · author #1
36. Preventing Oversmoothing in VAE via Generalized Variance Parameterization cs.LG · 2021 · author #3
37. Novelty Detection via Robust Variational Autoencoding cs.LG · 2020 · author #1
38. Inverse Problems, Deep Learning, and Symmetry Breaking cs.LG · 2020 · author #2
39. Robust Subspace Recovery Layer for Unsupervised Anomaly Detection cs.LG · 2019 · author #1

Mentions

• 2507.06613 #3 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2502.18197 #3 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2411.01135 #5 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2410.14758 #2 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2410.05116 #3 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2405.18503 #4 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2404.19228 #4 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2502.07636 #5 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2409.06096 #5 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2405.14822 #2 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2410.07761 #2 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2410.01796 #2 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2405.17251 #7 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2408.10807 #7 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2308.06979 #3 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2301.12811 #4 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2310.02279 #2 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2401.00365 #6 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2311.16424 #3 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2310.13267 #4 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2309.06934 #4 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2306.00367 #1 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2301.12686 #3 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2210.04296 #1 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2006.05534 #1 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2211.04124 #4 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2202.01987 #1 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2102.08663 #3 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2205.07547 #4 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 1904.00152 #1 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2003.09077 #2 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2602.09303 #5 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2601.20361 #5 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2601.22651 #3 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2602.18647 #7 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2603.07514 #1 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2510.21890 #1 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai
• 2410.00083 #3 · arxiv_oai · confidence 0.70 Chieh-Hsin Lai

Frequent Coauthors

• Yuki Mitsufuji 32 shared papers
• Yuhta Takida 24 shared papers
• Naoki Murata 19 shared papers
• Toshimitsu Uesaka 16 shared papers
• Stefano Ermon 11 shared papers
• Wei-Hsiang Liao 10 shared papers
• Takashi Shibuya 7 shared papers
• Dongjun Kim 6 shared papers
• Koichi Saito 5 shared papers
• Bac Nguyen 4 shared papers
• Woosung Choi 4 shared papers
• Che-Chia Chang 3 shared papers
• Chen-Yang Dai 3 shared papers
• Dongmian Zou 3 shared papers
• Gilad Lerman 3 shared papers
• Giorgio Fabbro 3 shared papers
• Ming-Chih Lai 3 shared papers
• Shusuke Takahashi 3 shared papers
• Stefan Uhlich 3 shared papers
• Te-Sheng Lin 3 shared papers