Related papers: DLIOS: An LLM-Augmented Real-Time Multi-Modal Inte…

Video Large Language Models (VideoLLMs) have achieved strong performance on many video understanding tasks, but most existing systems remain offline and are not well-suited for live video streams that require continuous observation and…

On-demand ride-hailing services like DiDi, Uber, and Lyft have transformed urban transportation, offering unmatched convenience and flexibility. In this paper, we introduce DiMA, an LLM-powered ride-hailing assistant deployed in DiDi…

With the rise of real-world human-AI interaction applications, such as AI assistants, the need for Streaming Video Dialogue is critical. To address this need, we introduce StreamMind, a video LLM framework that achieves ultra-FPS streaming…

This work proposes GLM-TTS, a production-level TTS system designed for efficiency, controllability, and high-fidelity speech generation. GLM-TTS follows a two-stage architecture, consisting of a text-to-token autoregressive model and a…

Supervised Fine-Tuning (SFT) Large Language Models (LLM) fundamentally rely on high-quality training data. While data selection and data synthesis are two common strategies to improve data quality, existing approaches often face limitations…

Existing video recommender systems rely primarily on user-defined metadata or on low-level visual and acoustic signals extracted by specialised encoders. These low-level features describe what appears on the screen but miss deeper semantics…

Large Language Models (LLMs), capable of handling multi-modal input and outputs such as text, voice, images, and video, are transforming the way we process information. Beyond just generating textual responses to prompts, they can integrate…

Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated…

Douyin Music, a large-scale platform with millions of daily users, adopts an immersive, feed-based discovery paradigm, where users passively explore music through continuous recommendations. While effective for passive music discovery, this…

Masked diffusion language models (MDLMs) promise fast, non-autoregressive text generation, yet existing samplers, which pick tokens to unmask based on model confidence, ignore interactions when unmasking multiple positions in parallel and…

Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language Models (LLMs) have empowered intelligent interaction…

In this paper, we introduce Dynamic Layer Operations (DLO), a novel approach for vertically scaling transformer-based Large Language Models (LLMs) by dynamically expanding, activating, or skipping layers using a sophisticated routing policy…

This paper introduces Interleaved Speech-Text Language Model (IST-LM) for zero-shot streaming Text-to-Speech (TTS). Unlike many previous approaches, IST-LM is directly trained on interleaved sequences of text and speech tokens with a fixed…

We present DreamLLM-3D, a composite multimodal AI system behind an immersive art installation for dream re-experiencing. It enables automated dream content analysis for immersive dream-reliving, by integrating a Large Language Model (LLM)…

Content-aware streaming requires dynamic, chunk-level importance weights to optimize subjective quality of experience (QoE). However, direct human annotation is prohibitively expensive while vision-saliency models generalize poorly. We…

The integration of experiment technologies with large language models (LLMs) is transforming scientific research, offering AI capabilities beyond specialized problem-solving to becoming research assistants for human scientists. In power…

Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive models, offering flexible generation orders and strong performance on complex reasoning tasks. However, instruction-tuned dLLMs exhibit a…

Large Language Models (LLMs) increasingly rely on inference-time reasoning algorithms such as chain-of-thought and multi-branch reasoning to improve accuracy on complex tasks. These methods, however, substantially increase token usage and…

Discrete speech units (DSUs) are derived from clustering the features of self-supervised speech models (S3Ms). DSUs offer significant advantages for on-device streaming speech applications due to their rich phonetic information, high…

Time series forecasting is central to data analysis and web technologies. The recent success of Large Language Models (LLMs) offers significant potential for this field, especially from the cross-modality aspect. Most methods adopt an…