Selected work

Representative Papers

Beyond the Smile: A Hybrid Convolutional VAE for Crypto Volatility Surfaces

Jun 15, 2026

This study addresses the challenge of reconstructing and forecasting cryptocurrency implied volatility surfaces under significant structural data sparsity. The authors propose a hybrid approach that integrates a convolutional variational autoencoder (CVAE) with deterministic maturity routing to fit the volatility smile quadratically. This work presents the first application of CVAE to crypto volatility surface modeling, enabling joint cross-asset training on Bitcoin (BTC) and Ethereum (ETH) and uncovering a shared latent manifold structure between them. The method simultaneously enforces calendar and butterfly no-arbitrage constraints, achieving a root mean squared error (RMSE) of 0.83 volatility points at 50% missingness—eight times lower than conventional smile-fitting techniques—and demonstrates superior capability in detecting market anomalies compared to existing approaches.

0 citationsRead paper

MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset

May 20, 2026

This work addresses the limitations of current large-scale text-to-image generation research, which is hindered by the absence of high-quality, deduplicated, diverse, and fine-grained annotated open datasets. To overcome this, the authors construct a dataset of 104.9 million high-quality image–text pairs from an initial pool of 2.9 billion raw samples through a multi-stage pipeline involving safety and domain filtering, exact and approximate deduplication, multimodal relabeling, and synthetic data augmentation. The resulting dataset is the first to simultaneously offer large scale, open licensing, non-redundancy, and rich semantic annotations, substantially lowering barriers to entry and enhancing reproducibility in the field. A 4-billion-parameter latent diffusion model trained on this dataset achieves strong performance on GenEval and DPG benchmarks.

0 citationsRead paper

LBM: Latent Bridge Matching for Fast Image-to-Image Translation

Mar 10, 2025

To address low inference efficiency and poor multi-task generalization in image-to-image translation—such as object removal, normal/depth estimation, controllable relighting, and shadow generation—this paper proposes Latent Bridge Matching (LBM), the first adaptation of Bridge Matching to latent space for single-step, conditional diffusion-based image translation. Our key contributions are: (1) a latent-space bridge matching mechanism that aligns cross-domain distributions via optimal transport; (2) a lightweight conditional latent encoder-decoder architecture enabling fine-grained control; and (3) a unified framework supporting diverse translation tasks efficiently. Extensive experiments demonstrate state-of-the-art performance across multiple benchmarks, with single-step inference significantly faster than iterative diffusion or GAN-based methods. The code is publicly available.

0 citationsRead paper

Recent publications

Latest Papers

Beyond the Smile: A Hybrid Convolutional VAE for Crypto Volatility Surfaces

Jun 15, 2026

This study addresses the challenge of reconstructing and forecasting cryptocurrency implied volatility surfaces under significant structural data sparsity. The authors propose a hybrid approach that integrates a convolutional variational autoencoder (CVAE) with deterministic maturity routing to fit the volatility smile quadratically. This work presents the first application of CVAE to crypto volatility surface modeling, enabling joint cross-asset training on Bitcoin (BTC) and Ethereum (ETH) and uncovering a shared latent manifold structure between them. The method simultaneously enforces calendar and butterfly no-arbitrage constraints, achieving a root mean squared error (RMSE) of 0.83 volatility points at 50% missingness—eight times lower than conventional smile-fitting techniques—and demonstrates superior capability in detecting market anomalies compared to existing approaches.

0 citationsRead paper

MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset

May 20, 2026

This work addresses the limitations of current large-scale text-to-image generation research, which is hindered by the absence of high-quality, deduplicated, diverse, and fine-grained annotated open datasets. To overcome this, the authors construct a dataset of 104.9 million high-quality image–text pairs from an initial pool of 2.9 billion raw samples through a multi-stage pipeline involving safety and domain filtering, exact and approximate deduplication, multimodal relabeling, and synthetic data augmentation. The resulting dataset is the first to simultaneously offer large scale, open licensing, non-redundancy, and rich semantic annotations, substantially lowering barriers to entry and enhancing reproducibility in the field. A 4-billion-parameter latent diffusion model trained on this dataset achieves strong performance on GenEval and DPG benchmarks.

0 citationsRead paper

LBM: Latent Bridge Matching for Fast Image-to-Image Translation

Mar 10, 2025

To address low inference efficiency and poor multi-task generalization in image-to-image translation—such as object removal, normal/depth estimation, controllable relighting, and shadow generation—this paper proposes Latent Bridge Matching (LBM), the first adaptation of Bridge Matching to latent space for single-step, conditional diffusion-based image translation. Our key contributions are: (1) a latent-space bridge matching mechanism that aligns cross-domain distributions via optimal transport; (2) a lightweight conditional latent encoder-decoder architecture enabling fine-grained control; and (3) a unified framework supporting diverse translation tasks efficiently. Extensive experiments demonstrate state-of-the-art performance across multiple benchmarks, with single-step inference significantly faster than iterative diffusion or GAN-based methods. The code is publicly available.

0 citationsRead paper