Related papers: Speculative Decoding for Autoregressive Video Gene…
Video large language models (Vid-LLMs) have shown strong capabilities in understanding video content. However, their reliance on dense video token representations introduces substantial memory and computational overhead in both prefilling…
Generating high-quality Scalable Vector Graphics (SVGs) from text remains a significant challenge. Existing LLM-based models that generate SVG code as a flat token sequence struggle with poor structural understanding and error accumulation,…
State-of-the-art Text-to-Video (T2V) diffusion models can generate visually impressive results, yet they still frequently fail to compose complex scenes or follow logical temporal instructions. In this paper, we argue that many errors,…
Although current Video-LLMs achieve impressive performance in video understanding tasks, their autoregressive decoding efficiency remains constrained by the massive number of video tokens. Visual token pruning can partially ease this…
Speculative decoding accelerates generation by drafting candidates and verifying them in parallel, yet state-of-the-art drafters (e.g., EAGLE) still require N sequential passes to propose N tokens. We present FastEagle, a non-autoregressive…
Speculative sampling is a popular technique for accelerating inference in Large Language Models by generating candidate tokens using a fast draft model and accepting or rejecting them based on the target model's distribution. While…
The current conditional autoregressive image generation methods have shown promising results, yet their potential remains largely unexplored in the practical unsupervised image translation domain, which operates without explicit…
Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models, particularly for real-time applications. While traditional optimization approaches like pruning and quantization often compromise model…
Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing training-free acceleration methods rely on binary cache-or-recompute decisions, overlooking…
Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…
Autoregressive video models offer distinct advantages over bidirectional diffusion models in creating interactive video content and supporting streaming applications with arbitrary duration. In this work, we present Next-Frame Diffusion…
Autoregressive visual generation has garnered increasing attention due to its scalability and compatibility with other modalities compared with diffusion models. Most existing methods construct visual sequences as spatial patches for…
Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of available computing…
Large language model (LLM) inference often suffers from high decoding latency and limited scalability across heterogeneous edge-cloud environments. Existing speculative decoding (SD) techniques accelerate token generation but remain…
Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any…
Auto-Regressive (AR) models have recently gained prominence in image generation, often matching or even surpassing the performance of diffusion models. However, one major limitation of AR models is their sequential nature, which processes…
Artificial Intelligence Generated Content (AIGC), particularly video generation with diffusion models, has been advanced rapidly. Invisible watermarking is a key technology for protecting AI-generated videos and tracing harmful content, and…
Speculative decoding and quantization effectively accelerate memory-bound inference of large language models. Speculative decoding mitigates the memory bandwidth bottleneck by verifying multiple tokens within a single forward pass, which…
Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…
Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small…