Related papers: Frame-Stacked Local Transformers For Efficient Mul…
Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision, language, and video understanding tasks, scaling them to long-form speech remains a critical bottleneck due to the explosive growth of…
Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While…
Current end-to-end spoken language models (SLMs) have made notable progress, yet they still encounter considerable response latency. This delay primarily arises from the autoregressive generation of speech tokens and the reliance on complex…
Unified architectures in multimodal large language models (MLLM) have shown promise in handling diverse tasks within a single framework. In the text-to-speech (TTS) task, current MLLM-based approaches rely on discrete token representations,…
Large Language Models (LLMs) are widely used in real-time voice chat applications, typically in combination with text-to-speech (TTS) systems to generate audio responses. However, their large size often leads to noticeable latency between…
Large language models (LLMs) are increasingly used for long-content generation (e.g., long Chain-of-Thought reasoning) where decoding efficiency becomes a critical bottleneck: Autoregressive decoding is inherently limited by its sequential…
Large Language Models (LLMs) are one of the most promising technologies for the next era of speech generation systems, due to their scalability and in-context learning capabilities. Nevertheless, they suffer from multiple stability issues…
Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals,…
As Large Language Models (LLMs) become increasingly integrated into many technological ecosystems across various domains and industries, identifying which model is deployed or being interacted with is critical for the security and…
Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive Language Models (ARMs), which generate…
Multilingual Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear. Do they form shared multilingual representations with language-specific decoding, and if so, why does…
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…
Large Language Models (LLMs) have revolutionised the field of Natural Language Processing (NLP) and have achieved state-of-the-art performance in practically every task in this field. However, the prevalent approach used in text generation,…
Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…
Decoding from large language models (LLMs) typically relies on fixed sampling hyperparameters (e.g., temperature, top-p), despite substantial variation in task difficulty and uncertainty across prompts and individual decoding steps. We…
Time series forecasting is critical across multiple domains, where time series data exhibit both local patterns and global dependencies. While Transformer-based methods effectively capture global dependencies, they often overlook short-term…
While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs…
Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…
We propose a novel class of language models, Latent Thought Models (LTMs), which incorporate explicit latent thought vectors that follow an explicit prior model in latent space. These latent thought vectors guide the autoregressive…
Large language models (LLMs) exhibit exceptional performance across a wide range of tasks; however, their token-by-token autoregressive generation process significantly hinders inference speed. Speculative decoding presents a promising…