Related papers: RecTok: Reconstruction Distillation along Rectifie…

Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each task, respectively. Existing approaches rely on spatial visual…

The ability to embed watermarks in images is a fundamental problem of interest for computer vision, and is exacerbated by the rapid rise of generated imagery in recent times. Current state-of-the-art techniques suffer from computational and…

Large-scale diffusion models have achieved remarkable performance in generative tasks. Beyond their initial training applications, these models have proven their ability to function as versatile plug-and-play priors. For instance, 2D…

Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decoding. However, realizing this potential in practice remains challenging: reducing the number of…

Visuomotor policies often leverage large pre-trained Vision Transformers (ViTs) for their powerful generalization capabilities. However, their significant data requirements present a major challenge in the data-scarce context of most…

While recent diffusion-based generative image codecs have shown impressive performance, their iterative sampling process introduces unpleasing latency. In this work, we revisit the design of a diffusion-based codec and argue that multi-step…

Diffusion Transformers achieve impressive generative quality but remain computationally expensive due to iterative sampling. Recently, dynamic resolution sampling has emerged as a promising acceleration technique by reducing the resolution…

Diffusion Transformer (DiT), a promising diffusion model for visual generation, demonstrates impressive performance but incurs significant computational overhead. Intriguingly, analysis of pre-trained DiT models reveals that global…

Recent advancements in text-to-video (T2V) generation have been driven by two competing paradigms: autoregressive language models and diffusion models. However, each paradigm has intrinsic limitations: language models struggle with visual…

This paper presents ThinkDiff, a novel alignment paradigm that empowers text-to-image diffusion models with multimodal in-context understanding and reasoning capabilities by integrating the strengths of vision-language models (VLMs).…

The Diffusion Transformer plays a pivotal role in advancing text-to-image and text-to-video generation, owing primarily to its inherent scalability. However, existing controlled diffusion transformer methods incur significant parameter and…

With the success of flow matching in visual generation, sampling efficiency remains a critical bottleneck for its practical application. Among flow models' accelerating methods, ReFlow has been somehow overlooked although it has theoretical…

Diffusion models have recently advanced photorealistic human synthesis, although practical talking-head generation (THG) remains constrained by high inference latency, temporal instability such as flicker and identity drift, and imperfect…

This paper addresses the challenge of achieving high-quality and fast image generation that aligns with complex human preferences. While recent advancements in diffusion models and distillation have enabled rapid generation, the effective…

Knowledge distillation is a popular technique for transferring the knowledge from a large teacher model to a smaller student model by mimicking. However, distillation by directly aligning the feature maps between teacher and student may…

Diffusion models achieve state-of-the-art generative performance but are fundamentally bottlenecked by their slow, iterative sampling process. While diffusion distillation techniques enable high-fidelity, few-step generation, traditional…

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective…

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…

Despite the burst of innovative methods for controlling the diffusion process, effectively controlling image styles in text-to-image generation remains a challenging task. Many adapter-based methods impose image representation conditions on…