Although text-to-image (T2I) models exhibit remarkable generation capabilities,they frequently fail to accurately bind semantically related objects or attributesin the input prompts; a challenge termed semantic binding. Previous approacheseither involve intensive fine-tuning of the entire T2I model or require users orlarge language models to specify generation layouts, adding complexity. In thispaper, we define semantic binding as the task of associating a given object with itsattribute, termed attribute binding, or linking it to other related sub-objects, referredto as object binding. We introduce a novel method called Token Merging (ToMe),which enhances semantic binding by aggregating relevant tokens into a singlecomposite token. This ensures that the object, its attributes and sub-objects all sharethe same cross-attention map.

Although text-to-image (T2I) models exhibit remarkable generation capabilities,they frequently fail to accurately bind semantically related objects or attributesin the input prompts; a challenge termed semantic binding. Previous approacheseither involve intensive fine-tuning of the entire T2I model or require users orlarge language models to specify generation layouts, adding complexity. In thispaper, we define semantic binding as the task of associating a given object with itsattribute, termed attribute binding, or linking it to other related sub-objects, referredto as object binding. We introduce a novel method called Token Merging (ToMe),which enhances semantic binding by aggregating relevant tokens into a singlecomposite token. This ensures that the object, its attributes and sub-objects all sharethe same cross-attention map.

Recent token reduction methods for Vision Transformers (ViTs) incorporate token merging, which measures the similarities between token embeddings and combines the most similar pairs. However, their merging policies are directly dependent on intermediate features in ViTs, which prevents exploiting features tailored for merging and requires end-to-end training to improve token merging. In this paper, we propose Decoupled Token Embedding for Merging (DTEM) that enhances token merging through a decoupled embedding learned via a continuously relaxed token merging process. Our method introduces a lightweight embedding module decoupled from the ViT forward pass to extract dedicated features for token merging, thereby addressing the restriction from using intermediate features. The continuously relaxed token merging, applied during training, enables us to learn the decoupled embeddings in a differentiable manner. Thanks to the decoupled structure, our method can be seamlessly integrated into existing ViT backbones and trained either modularly by learning only the decoupled embeddings or end-to-end by fine-tuning. We demonstrate the applicability of DTEM on various tasks, including classification, captioning, and segmentation, with consistent improvement in token merging. Especially in the ImageNet-1k classification, DTEM achieves a 37.2% reduction in FLOPs while maintaining a top-1 accuracy of 79.85% with DeiT-small. Code is available at \href{https://github.com/movinghoon/dtem}{link}.

Although text-to-image (T2I) models exhibit remarkable generation capabilities, they frequently fail to accurately bind semantically related objects or attributes in the input prompts; a challenge termed semantic binding. Previous approaches either involve intensive fine-tuning of the entire T2I model or require users or large language models to specify generation layouts, adding complexity. In this paper, we define semantic binding as the task of associating a given object with its attribute, termed attribute binding, or linking it to other related sub-objects, referred to as object binding. We introduce a novel method called Token Merging (ToMe), which enhances semantic binding by aggregating relevant tokens into a single composite token. This ensures that the object, its attributes and sub-objects all share the same cross-attention map. Additionally, to address potential confusion among main objects with complex textual prompts, we propose end token substitution as a complementary strategy. To further refine our approach in the initial stages of T2I generation, where layouts are determined, we incorporate two auxiliary losses, an entropy loss and a semantic binding loss, to iteratively update the composite token to improve the generation integrity. We conducted extensive experiments to validate the effectiveness of ToMe, comparing it against various existing methods on the T2I-CompBench and our proposed GPT-4o object binding benchmark. Our method is particularly effective in complex scenarios that involve multiple objects and attributes, which previous methods often fail to address. The code will be publicly available at \url{https://github.com/hutaihang/ToMe}.

Audio classification models, particularly the Audio Spectrogram Transformer (AST), play a crucial role in efficient audio analysis. However, optimizing their efficiency without compromising accuracy remains a challenge. In this paper, we introduce FastAST, a framework that integrates Token Merging (ToMe) into the AST framework. FastAST enhances inference speed without requiring extensive retraining by merging similar tokens in audio spectrograms. Furthermore, during training, FastAST brings about significant speed improvements. The experiments indicate that FastAST can increase audio classification throughput with minimal impact on accuracy. To mitigate the accuracy impact, we integrate Cross-Model Knowledge Distillation (CMKD) into the FastAST framework. Integrating ToMe and CMKD into AST results in improved accuracy compared to AST while maintaining faster inference speeds. FastAST represents a step towards real-time, resource-efficient audio analysis.

Diffusion Models (DMs) have exhibited superior performance in generating high-quality and diverse images. However, this exceptional performance comes at the cost of expensive architectural design, particularly due to the attention module heavily used in leading models. Existing works mainly adopt a retraining process to enhance DM efficiency. This is computationally expensive and not very scalable. To this end, we introduce the Attention-driven Training-free Efficient Diffusion Model (AT-EDM) framework that leverages attention maps to perform run-time pruning of redundant tokens, without the need for any retraining. Specifically, for single-denoising-step pruning, we develop a novel ranking algorithm, Generalized Weighted Page Rank (G-WPR), to identify redundant tokens, and a similarity-based recovery method to restore tokens for the convolution operation. In addition, we propose a Denoising-Steps-Aware Pruning (DSAP) approach to adjust the pruning budget across different denoising timesteps for better generation quality. Extensive evaluations show that AT-EDM performs favorably against prior art in terms of efficiency (e.g., 38.8% FLOPs saving and up to 1.53x speed-up over Stable Diffusion XL) while maintaining nearly the same FID and CLIP scores as the full model. Project webpage: https://atedm.github.io.

Keith Peiris says he started to see the generative AI writing on the wall six months ago. Peiris is the cofounder and chief executive of Tome, a San Francisco startup that makes presentation software juiced with generative AI. The company launched its product in early 2022 with a healthy cushion of 32 million in venture capital funding, and successfully surfed the ChatGPT hype wave after that, raising even more funding in early 2023. Venture capitalist and LinkedIn cofounder Reid Hoffman, former Google CEO and chairman Eric Schmidt, and Stability.ai's Tome had one problem, though: It wasn't generating meaningful revenue.

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy memory and computational costs to generate temporally-coherent frames, either in the form of diffusion inversion and/or cross-frame attention. In this paper, we conduct an analysis of such inefficiencies, and suggest simple yet effective modifications that allow significant speed-ups whilst maintaining quality. Moreover, we introduce Object-Centric Diffusion, coined as OCD, to further reduce latency by allocating computations more towards foreground edited regions that are arguably more important for perceptual quality. We achieve this by two novel proposals: i) Object-Centric Sampling, decoupling the diffusion steps spent on salient regions or background, allocating most of the model capacity to the former, and ii) Object-Centric 3D Token Merging, which reduces cost of cross-frame attention by fusing redundant tokens in unimportant background regions. Both techniques are readily applicable to a given video editing model \textit{without} retraining, and can drastically reduce its memory and computational cost. We evaluate our proposals on inversion-based and control-signal-based editing pipelines, and show a latency reduction up to 10x for a comparable synthesis quality.