Related papers: XQuery Streaming by Forest Transducers

We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor…

Previous multi-task dense prediction studies developed complex pipelines such as multi-modal distillations in multiple stages or searching for task relational contexts for each task. The core insight beyond these methods is to maximize the…

Database research can help machine learning performance in many ways. One way is to design better data structures. This paper combines the use of incremental computation and sequential and probabilistic filtering to enable "forgetful"…

Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which…

Learning-based 3D visual geometry models have significantly advanced with the advent of large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention to deliver robust and efficient streaming 3D reconstruction.…

XML document markup is highly repetitive and therefore well compressible using grammar-based compression. Downward, navigational XPath can be executed over grammar-compressed trees in PTIME: the query is translated into an automaton which…

Simultaneous Machine Translation is the task of incrementally translating an input sentence before it is fully available. Currently, simultaneous translation is carried out by translating each sentence independently of the previously…

Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio, thanks to their temporally uni-directional attention mechanism, which models correlations between the current token and previous…

Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However,…

We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction.…

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism…

Transformer-based models have dramatically increased their size and parameter count to tackle increasingly complex tasks. At the same time, there is a growing demand for high performance, low-latency inference on devices with limited…

Transformer-based acoustic modeling has achieved great suc-cess for both hybrid and sequence-to-sequence speech recogni-tion. However, it requires access to the full sequence, and thecomputational cost grows quadratically with respect to…

In this paper, I discuss the challenges in porting hydrodynamic codes to futuristic exascale HPC systems. In particular, we describe the computational complexities of finite difference method, pseudo-spectral method, and Fast Fourier…

Transformer-based models have emerged as promising tools for time series forecasting. However, these model cannot make accurate prediction for long input time series. On the one hand, they failed to capture global dependencies within time…

We discuss a key problem in information extraction which deals with wrapper failures due to changing content templates. A good proportion of wrapper failures are due to HTML templates changing to cause wrappers to become incompatible after…

Streaming generation models are utilized across fields, with the Transducer architecture being popular in industrial applications. However, its input-synchronous decoding mechanism presents challenges in tasks requiring non-monotonic…

In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio…

We consider an important generalization of the Steiner tree problem, the \emph{Steiner forest problem}, in the Euclidean plane: the input is a multiset $X \subseteq \mathbb{R}^2$, partitioned into $k$ color classes $C_1, C_2, \ldots, C_k…

Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…