Parameter-Efficient Fine-Tuning of State Space Models

Deep State Space Models (SSMs), such as Mamba (Gu & Dao, 2024), have emerged as powerful tools for language modeling, offering high performance with efficient inference and linear scaling in sequence length. However, the application of parameter-efficient fine-tuning (PEFT) methods to SSM-based models remains largely unexplored. This paper aims to systematically study two key questions: (i) How do existing PEFT methods perform on SSM-based models? (ii) Which modules are most effective for fine-tuning? We conduct an empirical benchmark of four basic PEFT methods on SSM-based models. Our findings reveal that prompt-based methods (e.g., prefix-tuning) are no longer effective, an empirical result further supported by theoretical analysis. In contrast, LoRA remains effective for SSM-based models. We further investigate the optimal application of LoRA within these models, demonstrating both theoretically and experimentally that applying LoRA to linear projection matrices without modifying SSM modules yields the best results, as LoRA is not effective at tuning SSM modules. To further improve performance, we introduce LoRA with Selective Dimension tuning (SDLoRA), which selectively updates certain channels and states on SSM modules while applying LoRA to linear projection matrices. Extensive experimental results show that this approach outperforms standard LoRA.

Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing

Diffusion models have achieved remarkable success in the domain of text-guided image generation and, more recently, in text-guided image editing. A commonly adopted strategy for editing real images involves inverting the diffusion process to obtain a noisy representation of the original image, which is then denoised to achieve the desired edits. However, current methods for diffusion inversion often struggle to produce edits that are both faithful to the specified text prompt and closely resemble the source image. To overcome these limitations, we introduce a novel and adaptable diffusion inversion technique for real image editing, which is grounded in a theoretical analysis of the role of $\eta$ in the DDIM sampling equation for enhanced editability. By designing a universal diffusion inversion method with a time- and region-dependent $\eta$ function, we enable flexible control over the editing extent. Through a comprehensive series of quantitative and qualitative assessments, involving a comparison with a broad array of recent methods, we demonstrate the superiority of our approach. Our method not only sets a new benchmark in the field but also significantly outperforms existing strategies. Our code is available at https://github.com/furiosa-ai/eta-inversion

Can MLLMs Perform Text-to-Image In-Context Learning?

The evolution from Large Language Models (LLMs) to Multimodal Large Language Models (MLLMs) has spurred research into extending In-Context Learning (ICL) to its multimodal counterpart. Existing such studies have primarily concentrated on image-to-text ICL. However, the Text-to-Image ICL (T2I-ICL), with its unique characteristics and potential applications, remains underexplored. To address this gap, we formally define the task of T2I-ICL and present CoBSAT, the first T2I-ICL benchmark dataset, encompassing ten tasks. Utilizing our dataset to benchmark six state-of-the-art MLLMs, we uncover considerable difficulties MLLMs encounter in solving T2I-ICL. We identify the primary challenges as the inherent complexity of multimodality and image generation. To overcome these challenges, we explore strategies like fine-tuning and Chain-of-Thought prompting, demonstrating notable improvements. Our code and dataset are available at \url{https://github.com/UW-Madison-Lee-Lab/CoBSAT}.

Counting Guidance for High Fidelity Text-to-Image Synthesis

Recently, the quality and performance of text-to-image generation significantly advanced due to the impressive results of diffusion models. However, text-to-image diffusion models still fail to generate high fidelity content with respect to the input prompt. One problem where text-to-diffusion models struggle is generating the exact number of objects specified in the text prompt. E.g. given a prompt "five apples and ten lemons on a table", diffusion-generated images usually contain the wrong number of objects. In this paper, we propose a method to improve diffusion models to focus on producing the correct object count given the input prompt. We adopt a counting network that performs reference-less class-agnostic counting for any given image. We calculate the gradients of the counting network and refine the predicted noise for each step. To handle multiple types of objects in the prompt, we use novel attention map guidance to obtain high-fidelity masks for each object. Finally, we guide the denoising process by the calculated gradients for each object. Through extensive experiments and evaluation, we demonstrate that our proposed guidance method greatly improves the fidelity of diffusion models to object count.

One-Shot Face Reenactment on Megapixels

The goal of face reenactment is to transfer a target expression and head pose to a source face while preserving the source identity. With the popularity of face-related applications, there has been much research on this topic. However, the results of existing methods are still limited to low-resolution and lack photorealism. In this work, we present a one-shot and high-resolution face reenactment method called MegaFR. To be precise, we leverage StyleGAN by using 3DMM-based rendering images and overcome the lack of high-quality video datasets by designing a loss function that works without high-quality videos. Also, we apply iterative refinement to deal with extreme poses and/or expressions. Since the proposed method controls source images through 3DMM parameters, we can explicitly manipulate source images. We apply MegaFR to various applications such as face frontalization, eye in-painting, and talking head generation. Experimental results show that our method successfully disentangles identity from expression and head pose, and outperforms conventional methods.