Related papers: DELTA: Language Diffusion-based EEG-to-Text Archit…

Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-right order. Existing alternatives still struggle to jointly achieve generation…

Chest X-ray report generation (CXR-RG) has the potential to substantially alleviate radiologists' workload. However, conventional autoregressive vision--language models (VLMs) suffer from high inference latency due to sequential token…

In this paper we present DELTA, a deep learning based language technology platform. DELTA is an end-to-end platform designed to solve industry level natural language and speech processing problems. It integrates most popular neural network…

Electroencephalography (EEG), with its broad range of applications, necessitates models that can generalize effectively across various tasks and datasets. Large EEG Models (LEMs) address this by pretraining encoder-centric architectures on…

Deciphering the intricacies of the human brain has captivated curiosity for centuries. Recent strides in Brain-Computer Interface (BCI) technology, particularly using motor imagery, have restored motor functions such as reaching, grasping,…

Electroencephalogram (EEG) decoding is a critical component of medical diagnostics, rehabilitation engineering, and brain-computer interfaces. However, contemporary decoding methodologies remain heavily dependent on task-specific datasets…

Recent research demonstrates the effectiveness of using pre-trained language models for legal case retrieval. Most of the existing works focus on improving the representation ability for the contextualized embedding of the [CLS] token and…

Decoding speech from stereo-electroencephalography (sEEG) signals has emerged as a promising direction for brain-computer interfaces (BCIs). Its clinical applicability, however, is limited by the inherent non-stationarity of neural signals,…

Developing foundation models for electroencephalography (EEG) remains challenging due to the signal's low signal-to-noise ratio and complex spectro-temporal non-stationarity. Existing approaches often overlook the hierarchical latent…

We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a natively integrated framework. Its architecture combines a fully semantic discrete tokenizer, a…

Continuous electroencephalography (EEG) is routinely used in neurocritical care to monitor seizures and other harmful brain activity, including rhythmic and periodic patterns that are clinically significant. Although deep learning methods…

Large language models (LLMs) have achieved reasonable quality improvements in machine translation (MT). However, most current research on MT-LLMs still faces significant challenges in maintaining translation consistency and accuracy when…

While Diffusion Models excel in text-to-image synthesis, they often suffer from concept omission when synthesizing complex multi-instance scenes. Existing training-free methods attempt to resolve this by rescaling attention maps, which…

In this work, we introduce LLaDA-V, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant…

Large language models (LLMs) demonstrate strong capabilities in natural language processing but remain prone to hallucinations, generating factually incorrect or fabricated content. This issue undermines their reliability, particularly in…

Distributional alignment enables large language models (LLMs) to predict how a target population distributes its responses across answer options, rather than collapsing disagreement into a single consensus answer. However, existing…

Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire…

The language model (LM) approach based on acoustic and linguistic prompts, such as VALL-E, has achieved remarkable progress in the field of zero-shot audio generation. However, existing methods still have some limitations: 1) repetitions,…

While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based models by a non-trivial margin. We identify a critical dilemma…

With recent advances of AIGC, video generation have gained a surge of research interest in both academia and industry (e.g., Sora). However, it remains a challenge to produce temporally aligned audio to synchronize the generated video,…