相关论文: Terminal Velocity Matching

Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception. However, existing methods lack flexible adaptivity, leading to irreversible detail loss and…

Training diffusion models for audiovisual sequences allows for a range of generation tasks by learning conditional distributions of various input-output combinations of the two modalities. Nevertheless, this strategy often requires training…

Transition videos play a crucial role in media production, enhancing the flow and coherence of visual narratives. Traditional methods like morphing often lack artistic appeal and require specialized skills, limiting their effectiveness.…

Generative models based on dynamical equations such as flows and diffusions offer exceptional sample quality, but require computationally expensive numerical integration during inference. The advent of consistency models has enabled…

Text-to-image diffusion inference typically follows synchronized schedules, where the numerical integrator advances the latent state to the same timestep at which the denoiser is conditioned. We propose an asynchronous inference mechanism…

While denoising diffusion and flow matching have driven major advances in generative modeling, their application to tabular data remains limited, despite its ubiquity in real-world applications. To this end, we develop TabbyFlow, a…

Distilling latent diffusion models (LDMs) into ones that are fast to sample from is attracting growing research interest. However, the majority of existing methods face two critical challenges: (1) They hinge on long training using a huge…

Recent advances in multimodal foundation models unifying image understanding and generation have opened exciting avenues for tackling a wide range of vision-language tasks within a single framework. Despite progress, existing unified models…

This paper presents FluxMem, a training-free framework for efficient streaming video understanding. FluxMem adaptively compresses redundant visual memory through a hierarchical, two-stage design: (1) a Temporal Adjacency Selection (TAS)…

Despite achieving state-of-the-art generation quality, diffusion models are hindered by the substantial computational burden of their iterative sampling process. While feature caching techniques achieve effective acceleration at higher step…

Time-varying meshes, characterized by dynamic connectivity and varying vertex counts, hold significant promise for applications such as augmented reality. However, their practical utilization remains challenging due to the substantial data…

Though rectified flow models have achieved remarkable performance in image, video, and 3D generation, their practical deployments are challenged by slow inference speeds. Prior acceleration methods reuse cached features from previous steps,…

Latent Diffusion Models (LDMs) are renowned for their powerful capabilities in image and video synthesis. Yet, compared to text-to-image (T2I) editing, text-to-video (T2V) editing suffers from a lack of decent temporal consistency and…

Recently, diffusion models have achieved significant advances in vision, text, and robotics. However, they still face slow generation speeds due to sequential denoising processes. To address this, a parallel sampling method based on Picard…

The integration of terahertz communications and ultra-massive multiple-input multiple-output (UM-MIMO) systems in 6G networks is motivated by their ability to enable unprecedented data rates, mitigate spectrum congestion, and enhance…

Flow map models such as Consistency Models (CM) and Mean Flow (MF) enable few-step generation by learning the long jump of the ODE solution of diffusion models, yet training remains unstable, sensitive to hyperparameters, and costly.…

Discrete flow matching generates text by iteratively transforming noise tokens into coherent language, but may require hundreds of forward passes. Distillation uses the multi-step trajectory to train a student to reproduce the process in a…

Recent advances in generative neural networks, particularly flow matching (FM), have enabled the generation of high-fidelity samples while significantly reducing computational costs. A promising application of these models is accelerating…

The Stable Diffusion Model (SDM) is a prevalent and effective model for text-to-image (T2I) and image-to-image (I2I) generation. Despite various attempts at sampler optimization, model distillation, and network quantification, these…

Atomic transport underpins the performance of materials in technologies such as energy storage and electronics, yet its simulation remains computationally demanding. In particular, modeling ionic diffusion in solid-state electrolytes (SSEs)…