Related papers: AReUReDi: Annealed Rectified Updates for Refining …

Typically, the significant efficiency can be achieved by deploying different edge AI models in various real world scenarios while a few large models manage those edge AI models remotely from cloud servers. However, customizing edge AI…

Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured…

Discrete diffusion models have emerged as a promising direction for vision-language tasks, offering bidirectional context modeling and theoretical parallelization. However, their practical application is severely hindered by a…

Developing efficient multi-objective optimization methods to compute the Pareto set of optimal compromises between conflicting objectives remains a key challenge, especially for large-scale and expensive problems. To bridge this gap, we…

Discrete Flow-based Models (DFMs) are powerful generative models for high-quality discrete data but typically suffer from slow sampling speeds due to their reliance on iterative decoding processes. This reliance on a multi-step process…

Deep neural networks demonstrate impressive performance in visual recognition, but they remain vulnerable to adversarial attacks that is imperceptible to the human. Although existing defense strategies such as adversarial training and…

Predicting future vehicle purchases among existing owners presents a critical challenge due to extreme class imbalance (<0.5% positive rate) and complex behavioral patterns. We propose REMEDI (Relative feature Enhanced Meta-learning with…

Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the de facto choice. Existing methods, however, train the student…

Diffusion models promise efficient parallel text generation but rely on bidirectional attention, creating a structural mismatch with pre-trained Autoregressive (AR) models. This incompatibility precludes reusing robust AR priors,…

Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired approaches, such as LlaDA and Dream, mitigate this by…

Masked diffusion language models enable parallel token generation and offer improved decoding efficiency over autoregressive models. However, their performance degrades significantly when generating multiple tokens simultaneously, due to a…

Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single…

Inversion-based image editing in flow matching models has emerged as a powerful paradigm for training-free, text-guided image manipulation. A central challenge in this paradigm is the injection dilemma: injecting source features during…

The rapid progress of large language models (LLMs) has catalyzed the emergence of multimodal large language models (MLLMs) that unify visual understanding and image generation within a single framework. However, most existing MLLMs rely on…

Diffusion models have shown great promise for image and video generation, but sampling from state-of-the-art models requires expensive numerical integration of a generative ODE. One approach for tackling this problem is rectified flows,…

Efficient design of biological sequences will have a great impact across many industrial and healthcare domains. However, discovering improved sequences requires solving a difficult optimization problem. Traditionally, this challenge was…

In the visual generative area, discrete diffusion models are gaining traction for their efficiency and compatibility. However, pioneered attempts still fall behind their continuous counterparts, which we attribute to noise (absorbing state)…

We introduce InVirtuoGen, a discrete flow generative model for fragmented SMILES for de novo and fragment-constrained generation, and target-property/lead optimization of small molecules. The model learns to transform a uniform source over…

The use of differential equations (ODE) is one of the most promising approaches to network inference. The success of ODE-based approaches has, however, been limited, due to the difficulty in estimating parameters and by their lack of…

Discrete diffusion models generate sequences by iteratively denoising samples corrupted by categorical noise, offering an appealing alternative to autoregressive decoding for structured and symbolic generation. However, standard training…