Related papers: Accelerating Auto-regressive Text-to-Image Generat…

As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also restricts the model to generate tokens one by one, forming a…

Autoregressive (AR) image models achieve diffusion-level quality but suffer from sequential inference, requiring approximately 2,000 steps for a 576x576 image. Speculative decoding with draft trees accelerates LLMs yet underperforms on…

Modern Text-to-Image (T2I) generation increasingly relies on token-centric architectures that are trained with self-supervision, yet effectively fusing text with visual tokens remains a challenge. We propose \textbf{JEPA-T}, a unified…

Reasoning models excel by generating long chain-of-thoughts, but decoding the resulting thousands of tokens is slow. Token-level speculative decoding (SD) helps, but its benefit is capped, because the chance that an entire $\gamma$-token…

Current auto-regressive models can generate high-quality, topologically precise meshes; however, they necessitate thousands-or even tens of thousands-of next-token predictions during inference, resulting in substantial latency. We introduce…

Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, focusing on two critical factors: whether…

Autoregressive models excel in sequential modeling and have proven to be effective for vision-language data. However, the spatial nature of visual signals conflicts with the sequential dependencies of next-token prediction, leading to…

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the…

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

Vision-language Models (VLMs) have made significant strides in visual understanding and query response generation, but often face challenges of high computational cost and inference latency due to autoregressive decoding. In this work, we…

Artificial Intelligence-Generated Content (AIGC) has made significant strides, with high-resolution text-to-image (T2I) generation becoming increasingly critical for improving users' Quality of Experience (QoE). Although…

Speculative Decoding (SD) is a widely used approach to accelerate the inference of large language models (LLMs) without reducing generation quality. It operates by first using a compact model to draft multiple tokens efficiently, followed…

Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising over all spatial tokens. Dynamic-resolution sampling reduces this cost by performing…

In this paper we propose a new generative model of text, Step-unrolled Denoising Autoencoder (SUNDAE), that does not rely on autoregressive models. Similarly to denoising diffusion techniques, SUNDAE is repeatedly applied on a sequence of…

Speculative decoding accelerates large language model inference using a smaller draft model. In this paper, we establish a surprising connection between speculative decoding and channel simulation, which aims at simulating a noisy channel…

The goal of this paper is to accelerate codec-based speech synthesis systems with minimum sacrifice to speech quality. We propose an enhanced inference method that allows for flexible trade-offs between speed and quality during inference…

Standard autoregressive language models generate text by repeatedly selecting a discrete next token, coupling prediction with irreversible commitment at every step. We show that token selection is not the only viable autoregressive…

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Consistent text-to-image (T2I) generation seeks to produce identity-preserving images of the same subject across diverse scenes, yet it often fails due to a phenomenon called identity (ID) shift. Previous methods have tackled this issue,…

Speculative decoding (SD), where an extra draft model is employed to provide multiple draft tokens first, and then the original target model verifies these tokens in parallel, has shown great power for LLM inference acceleration. However,…