Related papers: Orthrus: Memory-Efficient Parallel Token Generatio…

Diffusion-based large language models (dLLMs), despite their promising performance, still suffer from inferior inference efficiency. This is because dLLMs rely on bidirectional attention and cannot directly benefit from the standard…

Diffusion Transformer (DiT)-based video diffusion models generate high-quality videos at scale but incur prohibitive processing latency and memory costs for long videos. To address this, we propose a novel distributed inference strategy,…

Despite remarkable progress in autoregressive language models, alternative generative paradigms beyond left-to-right generation are still being actively explored. Discrete diffusion models, with the capacity for parallel generation, have…

Deep generative models have advanced rapidly across text and vision, motivating unified multimodal systems that can understand, reason over, and generate interleaved text-image sequences. Most existing approaches combine autoregressive…

The design of high-performance optical systems remains a specialized domain gated by the limited availability of expert engineers, creating a bottleneck that stalls innovation despite the growing demand for imaging hardware. While deep…

With the impressive generative capabilities of diffusion models, personalized content synthesis has emerged as the most highly anticipated. However, the large model sizes and iterative nature of inference make it difficult to deploy…

Recent studies on end-to-end (E2E) speech generation with large language models (LLMs) have attracted significant community attention, with multiple works extending text-based LLMs to generate discrete speech tokens. Existing E2E approaches…

Diffusion Language Models (DLMs) decode multiple tokens in parallel, but aggressive multi-token decoding amplifies cross-token dependency errors and can sharply degrade generation quality. We propose BackPlay, a frozen-backbone…

Diffusion Transformers (DiTs) achieve superior image generation quality but suffer from quadratic computational complexity relative to token count. While various token reduction (TR) methods have been proposed to mitigate this cost, they…

Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memory usage due to…

Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…

Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequential decoding. Unlike autoregressive…

Online inference is becoming a key service product for many businesses, deployed in cloud platforms to meet customer demands. Despite their revenue-generation capability, these services need to operate under tight Quality-of-Service (QoS)…

Large-scale digitization initiatives have unlocked massive collections of historical newspapers, yet effective computational access remains hindered by OCR corruption, multilingual orthographic variation, and temporal language drift. We…

Parameter-efficient fine-tuning enables fast personalization of text-to-image diffusion models, but composing multiple custom concepts remains challenging due to representation interference. Existing modular methods either rely on expensive…

Diffusion models have recently shown promising results for video super-resolution (VSR). However, directly adapting generative diffusion models to VSR can result in redundancy, since low-quality videos already preserve substantial content…

Optimising deep learning inference across edge devices and optimisation targets such as inference time, memory footprint and power consumption is a key challenge due to the ubiquity of neural networks. Today, production deep learning…

Diffusion Language Models (DLMs) are often advertised as enabling parallel token generation, yet practical fast DLMs frequently converge to left-to-right, autoregressive (AR)-like decoding dynamics. In contrast, genuinely non-AR generation…

Latent Diffusion models (LDMs) have achieved remarkable results in synthesizing high-resolution images. However, the iterative sampling process is computationally intensive and leads to slow generation. Inspired by Consistency Models (song…

Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token generation that can lead to significant throughput advantages and superior GPU utilization over the traditional…