Related papers: When to Lock Attention: Training-Free KV Control i…
Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them…
Diffusion language models offer parallel token generation and inherent bidirectionality, promising more efficient and powerful sequence modeling compared to autoregressive approaches. However, state-of-the-art diffusion models (e.g., Dream…
Through systematic experiments on long-context generation, we observe a damaging failure mode in which decoding can collapse into persistent repetition loops. We find that this degeneration is driven by collapsed attention patterns, where a…
Video generative models achieve high-quality synthesis from natural-language prompts by leveraging large-scale web data. However, this training paradigm inherently exposes them to unsafe biases and harmful concepts, introducing the risk of…
Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic…
Latent Video Diffusion Models (LVDMs) have achieved state-of-the-art generative quality for image and video generation; however, they remain brittle under noisy conditioning, where small perturbations in text or multimodal embeddings can…
We propose \textbf{IC-Effect}, an instruction-guided, DiT-based framework for few-shot video VFX editing that synthesizes complex effects (\eg flames, particles and cartoon characters) while strictly preserving spatial and temporal…
Video colour editing is a crucial task for content creation, yet existing solutions either require painstaking frame-by-frame manipulation or produce unrealistic results with temporal artefacts. We present a practical, training-free…
Although powerful for image generation, consistent and controllable video is a longstanding problem for diffusion models. Video models require extensive training and computational resources, leading to high costs and large environmental…
Sequence-to-sequence tasks often benefit from long contexts, but the quadratic complexity of self-attention in standard Transformers renders this non-trivial. During generation, temporary representations -stored in the so-called KV…
Existing Large Vision-Language Models (LVLMs) exhibit insufficient visual attention, leading to hallucinations. To alleviate this problem, some previous studies adjust and amplify visual attention. These methods present a limitation that…
Diffusion models have demonstrated remarkable success in image generation and editing, with recent advancements enabling albedo-preserving image relighting. However, applying these models to video relighting remains challenging due to the…
Diffusion Transformer has shown remarkable abilities in generating high-fidelity videos, delivering visually coherent frames and rich details over extended durations. However, existing video generation models still fall short in…
Diffusion models have demonstrated impressive performance in text-to-image generation. They utilize a text encoder and cross-attention blocks to infuse textual information into images at a pixel level. However, their capability to generate…
Sign language translation (SLT) is challenging, as it involves converting sign language videos into natural language. Previous studies have prioritized accuracy over diversity. However, diversity is crucial for handling lexical and…
Diffusion models excel at photorealistic synthesis but struggle with precise object counts, especially in high-density settings. We introduce COUNTLOOP, a training-free framework that achieves precise instance control through iterative,…
Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…
In this work, we investigate the capability of generating images from pre-trained diffusion models at much higher resolutions than the training image sizes. In addition, the generated images should have arbitrary image aspect ratios. When…
We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our…
Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements…