Related papers: Syndrome-Flow Consistency Model Achieves One-step …
Text normalization is a ubiquitous process that appears as the first step of many Natural Language Processing problems. However, previous Deep Learning approaches have suffered from so-called silly errors, which are undetectable on…
In order to realize fault-tolerant quantum computation, tight evaluation of error threshold under practical noise models is essential. While non-Clifford noise is ubiquitous in experiments, the error threshold under non-Clifford noise…
At the heart of time-series forecasting (TSF) lies a fundamental challenge: how can models efficiently and effectively capture long-range temporal dependencies across ever-growing sequences? While deep learning has brought notable progress,…
In ECOC framework, the ternary coding strategy is widely deployed in coding process. It relabels classes with {"-1,0,1" }, where -1/1 means to assign the corresponding classes to the negative/positive group, and label 0 leads to ignore the…
Dense optical flow estimation is challenging when there are large displacements in a scene with heterogeneous motion dynamics, occlusion, and scene homogeneity. Traditional approaches to handle these challenges include hierarchical and…
Communication compression is essential for scalable distributed training of modern machine learning models, but it often degrades convergence due to the noise it introduces. Error Feedback (EF) mechanisms are widely adopted to mitigate this…
Looped transformers scale computational depth without increasing parameter count by repeatedly applying a shared transformer block and can be used for iterative refinement, where each loop rewrites a full fixed-size prediction in parallel.…
Diffusion models (DM) can gradually learn to remove noise, which have been widely used in artificial intelligence generated content (AIGC) in recent years. The property of DM for removing noise leads us to wonder whether DM can be applied…
In this paper, we propose an iterative source error correction (ISEC) decoding scheme for deep-learning-based joint source-channel coding (Deep JSCC). Given a noisy codeword received through the channel, we use a Deep JSCC encoder and…
Although Diffusion Transformer (DiT) has emerged as a predominant architecture for image and video generation, its iterative denoising process results in slow inference, which hinders broader applicability and development. Caching-based…
Flow matching as a paradigm of generative model achieves notable success across various domains. However, existing methods use either multi-round training or knowledge within minibatches, posing challenges in finding a favorable coupling…
Quantum error correction (QEC) with single-shot decoding enables reduction of errors after every single round of noisy stabilizer measurement, easing the time-overhead requirements for fault tolerance. Notably, several classes of quantum…
Diffusion and flow matching (FM) models have achieved remarkable progress in speech enhancement (SE), yet their dependence on multi-step generation is computationally expensive and vulnerable to discretization errors. Recent advances in…
Accurately predicting future pedestrian trajectories is crucial across various domains. Due to the uncertainty in future pedestrian trajectories, it is important to learn complex spatio-temporal representations in multi-agent scenarios. To…
Inverse problems, which involve estimating parameters from incomplete or noisy observations, arise in various fields such as medical imaging, geophysics, and signal processing. These problems are often ill-posed, requiring regularization…
Neural operator surrogates for time-dependent partial differential equations (PDEs) conventionally employ autoregressive prediction schemes, which accumulate error over long rollouts and require uniform temporal discretization. We introduce…
Key-point-based scene understanding is fundamental for autonomous driving applications. At the same time, optical flow plays an important role in many vision tasks. However, due to the implicit bias of equal attention on all points, classic…
When concept drift is detected during classification in a data stream, a common remedy is to retrain a framework's classifier. However, this loses useful information if the classifier has learnt the current concept well, and this concept…
Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation. To overcome this limitation, we propose consistency models, a new…
Accurately recovering images from phaseless measurements is a challenging and long-standing problem. In this work, we present "deepECpr," which combines expectation-consistent (EC) approximation with deep denoising networks to surpass…