Yijun Li

In video diffusion transformers, visual patch tokens maintain explicit correspondence to space and time. We hypothesize that their channel dimension can serve as a semantic control space, which we call Visual Dial Space V ⁺ . In this space, additive directions can be broadcast to the token stream to control appearance or motion attributes, enabling slider-style edits such as making a generated person look older or run faster. To verify the hypothesis, we present TokenDial , a framework for learning attribute directions in the proposed V ⁺ space. TokenDial keeps the pretrained video generator frozen and optimizes only additive directions. Rather than requiring paired edited videos, TokenDial supervises each direction through its induced effect on generated videos: the edited video should move along the desired attribute while the remaining content stays stable. The learned directions become reusable visual dials that support continuous appearance and motion control, explicit spatiotemporal localization, composition, and reuse across prompts, resolutions, and video lengths. Experiments and human studies show that TokenDial achieves stronger slider controllability and better content preservation than prior video editing and slider-based methods. Project page: https://tokendial.github.io/

In this paper, we introduce a model designed to improve the prediction of image-text alignment, targeting the challenge of compositional understanding in current visual-language models. Our approach focuses on generating high-quality training datasets for the alignment task by producing mixed-type negative captions derived from positive ones. Critically, we address the distribution imbalance between positive and negative captions to ensure that the alignment model does not depend solely on textual information but also considers the associated images for predicting alignment accurately. By creating this enhanced training data, we fine-tune an existing leading visual-language model to boost its capability in understanding alignment. Our model significantly outperforms current top-performing methods across various datasets. We also demonstrate the applicability of our model by ranking the images generated by text-to-image models based on text alignment. Project page: \url{https://yuheng-li.github.io/LLaVA-score/}

Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object generation. In this work, we first show the fundamental reasons for such misalignment by identifying issues related to low attention activation and mask overlaps. Then we propose a compositional finetuning framework with two novel objectives, the Separate loss and the Enhance loss, that reduce object mask overlaps and maximize attention scores, respectively. Unlike conventional test-time adaptation methods, our model, once finetuned on critical parameters, is able to directly perform inference given an arbitrary multi-object prompt, which enhances the scalability and generalizability. Through comprehensive evaluations, our model demonstrates superior performance in image realism, text-image alignment, and adaptability, significantly surpassing established baselines. Furthermore, we show that training our model with a diverse range of concepts enables it to generalize effectively to novel concepts, exhibiting enhanced performance compared to models trained on individual concept pairs.

Existing GAN inversion and editing methods work well for aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categories with complex scene layouts and object occlusions, such as cars, animals, and outdoor images. We propose a new method to invert and edit such complex images in the latent space of GANs, such as StyleGAN2. Our key idea is to explore inversion with a collection of layers, spatially adapting the inversion process to the difficulty of the image. We learn to predict the "invertibility" of different image segments and project each segment into a latent layer. Easier regions can be inverted into an earlier layer in the generator's latent space, while more challenging regions can be inverted into a later feature space. Experiments show that our method obtains better inversion results compared to the recent approaches on complex categories, while maintaining downstream editability. Please refer to our project page at https://www.cs.cmu.edu/~SAMInversion.

Generative adversarial networks (GANs), e.g., StyleGAN2, play a vital role in various image generation and synthesis tasks, yet their notoriously high computational cost hinders their efficient deployment on edge devices. Directly applying generic compression approaches yields poor results on GANs, which motivates a number of recent GAN compression works. While prior works mainly accelerate conditional GANs, e.g., pix2pix and CycleGAN, compressing state-of-the-art unconditional GANs has rarely been explored and is more challenging. In this paper, we propose novel approaches for unconditional GAN compression. We first introduce effective channel pruning and knowledge distillation schemes specialized for unconditional GANs. We then propose a novel content-aware method to guide the processes of both pruning and distillation. With content-awareness, we can effectively prune channels that are unimportant to the contents of interest, e.g., human faces, and focus our distillation on these regions, which significantly enhances the distillation quality. On StyleGAN2 and SN-GAN, we achieve a substantial improvement over the state-of-the-art compression method. Notably, we reduce the FLOPs of StyleGAN2 by 11x with visually negligible image quality loss compared to the full-size model. More interestingly, when applied to various image manipulation tasks, our compressed model forms a smoother and better disentangled latent manifold, making it more effective for image editing.