Related papers: Hybrid Autoregressive-Diffusion Model for Real-Tim…
The diversity of sign representation is essential for Sign Language Production (SLP) as it captures variations in appearance, facial expressions, and hand movements. However, existing SLP models are often unable to capture diversity while…
How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent…
Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on…
Spoken Language Understanding (SLU), a core component of the task-oriented dialogue system, expects a shorter inference latency due to the impatience of humans. Non-autoregressive SLU models clearly increase the inference speed but suffer…
Sign Language Production (SLP) aims to generate semantically consistent sign videos from textual statements, where the conversion from textual glosses to sign poses (G2P) is a crucial step. Existing G2P methods typically treat sign poses as…
Diffusion-based Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive models, offering unique advantages through bidirectional attention and parallel generation paradigms. However, the generation results…
Sign language translation (SLT) is challenging, as it involves converting sign language videos into natural language. Previous studies have prioritized accuracy over diversity. However, diversity is crucial for handling lexical and…
Sign language generation aims to produce diverse sign representations based on spoken language. However, achieving realistic and naturalistic generation remains a significant challenge due to the complexity of sign language, which…
While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically,…
In this work, we propose a two-stage sign language production (SLP) paradigm that first encodes sign language sequences into discrete codes and then autoregressively generates sign language from text based on the learned codebook. However,…
Most large language models are autoregressive: they generate tokens one at a time. Discrete diffusion language models can generate multiple tokens in parallel, but sampling from them requires a denoising order: a strategy for deciding which…
Diffusion models have shown promise in text generation, but often struggle with generating long, coherent, and contextually accurate text. Token-level diffusion doesn't model word-order dependencies explicitly and operates on short, fixed…
In this work, we propose DARSLP, a simple gloss-free, transformer-based sign language production (SLP) framework that directly maps spoken-language text to sign pose sequences. We first train a pose autoencoder that encodes sign poses into…
Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models, offering the potential for parallel token generation and bidirectional context modeling. However, harnessing this flexibility…
Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent…
Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…
Diffusion Language Models (DLMs) provide a promising alternative to autoregressive language models by generating text through iterative denoising and bidirectional refinement. However, this iterative generation paradigm also introduces…
Autoregressive (AR) Large Language Models (LLMs) have demonstrated significant success across numerous tasks. However, the AR modeling paradigm presents certain limitations; for instance, contemporary autoregressive LLMs are trained to…
Generating natural and linguistically accurate sign language avatars remains a formidable challenge. Current Sign Language Production (SLP) frameworks face a stark trade-off: direct text-to-pose models suffer from regression-to-the-mean…
Discrete diffusion models have recently shown significant progress in modeling complex data, such as natural languages and DNA sequences. However, unlike diffusion models for continuous data, which can generate high-quality samples in just…