Related papers: DiffuMamba: High-Throughput Diffusion LMs with Mam…

The goal of style transfer is, given a content image and a style source, generating a new image preserving the content but with the artistic representation of the style source. Most of the state-of-the-art architectures use transformers or…

Recent Speech Large Language Models~(LLMs) have achieved impressive capabilities in end-to-end speech interaction. However, the prevailing autoregressive paradigm imposes strict serial constraints, limiting generation efficiency and…

Current Video Large Language Models (Video LLMs) typically encode frames via a vision encoder and employ an autoregressive (AR) LLM for understanding and generation. However, this AR paradigm inevitably faces a dual efficiency bottleneck:…

With the evolution of large language models, traditional Transformer models become computationally demanding for lengthy sequences due to the quadratic growth in computation with respect to the sequence length. Mamba, emerging as a…

While autoregressive (AR) Vision-Language-Action (VLA) models have demonstrated formidable reasoning capabilities in robotic tasks, their sequential decoding process often incurs high inference latency and may amplify error accumulation…

Deep learning-based single-channel speaker separation has improved significantly in recent years largely due to the introduction of the transformer-based attention mechanism. However, these improvements come at the expense of intense…

Vision-language models (VLMs) predominantly rely on autoregressive decoding, which generates tokens one at a time and fundamentally limits inference throughput. This limitation is especially acute in physical AI scenarios such as robotics…

Diffusion Models have become a cornerstone of modern generative AI for their exceptional generation quality and controllability. However, their inherent \textit{multi-step iterations} and \textit{complex backbone networks} lead to…

Mamba is a newly proposed architecture which behaves like a recurrent neural network (RNN) with attention-like capabilities. These properties are promising for speaker diarization, as attention-based models have unsuitable memory…

Multilingual automatic speech recognition (ASR) remains a challenging task, especially when balancing performance across high- and low-resource languages. Recent advances in sequence modeling suggest that architectures beyond Transformers…

This paper shows how diffusion language models (DLMs) can be used as effective and efficient retrievers. Existing DLM-based retrievers (e.g., DiffEmbed) follow BERT-style encoding, representing each query or passage as a single mean-pooled…

Transformer and its derivatives have achieved success in diverse tasks across computer vision, natural language processing, and speech processing. To reduce the complexity of computations within the multi-head self-attention mechanism in…

In the information retrieval (IR) area, dense retrieval (DR) models use deep learning techniques to encode queries and passages into embedding space to compute their semantic relations. It is important for DR models to balance both…

Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions, limiting the exploitation of non-local receptive fields. In response to this issue, we introduce a novel dual-branch…

We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions,…

Discrete diffusion models offer global context awareness and flexible parallel generation. However, uniform random noise schedulers in standard DLLM training overlook the highly non-uniform information density inherent in real-world…

Recent advancements in diffusion models have significantly improved symbolic music generation. However, most approaches rely on transformer-based architectures with self-attention mechanisms, which are constrained by quadratic computational…

Diffusion language models (DLMs) have recently emerged as an alternative to autoregressive approaches, offering parallel sequence generation and flexible token orders. However, their inference remains slower than that of autoregressive…

While recent Multimodal Large Language Models (MLLMs) have attained significant strides in multimodal reasoning, their reasoning processes remain predominantly text-centric, leading to suboptimal performance in complex long-horizon,…

Existing CNN-based speech separation models face local receptive field limitations and cannot effectively capture long time dependencies. Although LSTM and Transformer-based speech separation models can avoid this problem, their high…