Related papers: Revoking Amnesia: RL-based Trajectory Optimization…
While deep neural networks (NN) significantly advance image compressed sensing (CS) by improving reconstruction quality, the necessity of training current CS NNs from scratch constrains their effectiveness and hampers rapid deployment.…
As large-scale diffusion models continue to advance, they excel at producing high-quality images but often generate unwanted content, such as sexually explicit or violent content. Existing methods for concept removal generally guide the…
Recent advances in text-to-video generation have demonstrated the utility of powerful diffusion models. Nevertheless, the problem is not trivial when shaping diffusion models to animate static image (i.e., image-to-video generation). The…
Bridging the gap between diffusion models and human preferences is crucial for their integration into practical generative workflows. While optimizing downstream reward models has emerged as a promising alignment strategy, concerns arise…
Dense Associative Memories (DenseAMs) are generalizations of Hopfield networks, which have superior information storage capacity and can store training data points (memories) at local minima of the energy landscape. When the amount of…
Image rescaling aims to learn the optimal low-resolution (LR) image that can be accurately reconstructed to its original high-resolution (HR) counterpart, providing an efficient image processing and storage method for ultra-high definition…
Concept erasure is extensively utilized in image generation to prevent text-to-image models from generating undesired content. Existing methods can effectively erase narrow concepts that are specific and concrete, such as distinct…
Generative diffusion models for end-to-end autonomous driving often suffer from mode collapse, tending to generate conservative and homogeneous behaviors. While DiffusionDrive employs predefined anchors representing different driving…
The rapid growth of text-to-video (T2V) diffusion models has raised concerns about privacy, copyright, and safety due to their potential misuse in generating harmful or misleading content. These models are often trained on numerous…
Diffusion models dominate the space of text-to-image generation, yet they may produce undesirable outputs, including explicit content or private data. To mitigate this, concept ablation techniques have been explored to limit the generation…
While diffusion models demonstrate strong generative capabilities in image restoration (IR) tasks, their complex architectures and iterative processes limit their practical application compared to mainstream reconstruction-based general…
This work presents Robust Representation Learning via Adaptive Mask (RAM++), a two-stage framework for all-in-one image restoration. RAM++ integrates high-level semantic understanding with low-level texture generation to achieve…
We propose an image restoration algorithm that can control the perceptual quality and/or the mean square error (MSE) of any pre-trained model, trading one over the other at test time. Our algorithm is few-shot: Given about a dozen images…
Fine-tuning based concept erasing has demonstrated promising results in preventing generation of harmful contents from text-to-image diffusion models by removing target concepts while preserving remaining concepts. To maintain the…
Instructional video editing applies edits to an input video using only text prompts, enabling intuitive natural-language control. Despite rapid progress, most methods still require fixed-length inputs and substantial compute. Meanwhile,…
We present Diffusion Restore, a real-time framework for diffusion-based MCMC light transport. MCMC methods are highly suitable for sampling from complex high-dimensional distributions and for approximating integrals over them. In practice,…
Information retrieval (IR) in dynamic data streams is a crucial task, as shifts in data distribution degrade the performance of AI-powered IR systems. To mitigate this issue, memory-based continual learning has been widely adopted for IR.…
Continual learning -- the ability to acquire knowledge incrementally without forgetting previous skills -- is fundamental to natural intelligence. While the human brain excels at this, artificial neural networks struggle with "catastrophic…
While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating…
Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for downstream alignment. Existing trajectory-based RL…