Related papers: KV-Edit: Training-Free Image Editing for Precise B…

Key-value (KV) caching is widely used to accelerate transformer inference, but its memory cost grows linearly with input length, limiting long-context deployment. Existing token eviction methods reduce memory by discarding less important…

Large Language Models (LLMs) use key-value (KV) cache to reduce redundant computation in autoregressive generation. However, the KV cache size increases linearly during generation, leading to excessive memory usage, especially for long…

The key-value (KV) cache accelerates LLMs decoding by storing KV tensors from previously generated tokens. It reduces redundant computation at the cost of increased memory usage. To mitigate this overhead, existing approaches compress KV…

Image-driven video editing aims to propagate edit contents from the modified first frame to the remaining frames. Existing methods usually invert the source video to noise using a pre-trained image-to-video (I2V) model and then guide the…

Leveraging the powerful generation capability of large-scale pretrained text-to-image models, training-free methods have demonstrated impressive image editing results. Conventional diffusion-based methods, as well as recent rectified flow…

Replacing the background and simultaneously adjusting foreground objects is a challenging task in image editing. Current techniques for generating such images relies heavily on user interactions with image editing softwares, which is a…

When transformer-based language models are deployed for text generation, most of the inference time is spent in the decoding stage, where output tokens are generated sequentially. Reducing the hardware cost of each decoding step is…

Running Large Language Models (LLMs) on edge devices is crucial for reducing latency, improving real-time processing, and enhancing privacy. By performing inference directly on the device, data does not need to be sent to the cloud,…

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Vector quantization approaches (VQ-VAE, VQ-GAN) learn discrete neural representations of images, but these representations are inherently position-dependent: codes are spatially arranged and contextually entangled, requiring autoregressive…

Instruction-based video editing has witnessed rapid progress, yet current methods often struggle with precise visual control, as natural language is inherently limited in describing complex visual nuances. Although reference-guided editing…

Text-guided image editing has advanced rapidly with the rise of diffusion models. While flow-based inversion-free methods offer high efficiency by avoiding latent inversion, they often fail to effectively integrate source information,…

Advancements in diffusion models have enabled effortless image editing via text prompts, raising concerns about image security. Attackers with access to user images can exploit these tools for malicious edits. Recent defenses attempt to…

High-quality 3D scene reconstruction has recently advanced toward generalizable feed-forward architectures, enabling the generation of complex environments in a single forward pass. However, despite their strong performance in static scene…

Streaming video understanding requires processing unbounded video streams with limited memory and computation, posing two key challenges. First, continuously constructing new and evicting old key-value(KV) caches is required for unbounded…

We propose a zero-shot approach to image harmonization, aiming to overcome the reliance on large amounts of synthetic composite images in existing methods. These methods, while showing promising results, involve significant training…

Recent breakthroughs in text-to-image diffusion models have significantly advanced the generation of high-fidelity, photo-realistic images from textual descriptions. Yet, these models often struggle with interpreting spatial arrangements…

Diffusion models have revolutionized text-driven video editing. However, applying these methods to real-world editing encounters two significant challenges: (1) the rapid increase in GPU memory demand as the number of frames grows, and (2)…

Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. However, their increased computational and memory demands present significant…

Diffusion models have made significant advances in generating high-quality images, but their application to video generation has remained challenging due to the complexity of temporal motion. Zero-shot video editing offers a solution by…