相关论文: Accelerating Streaming Video Large Language Models…

The development of Multi-modal Large Language Models (MLLMs) enhances Large Language Models (LLMs) with the ability to perceive data formats beyond text, significantly advancing a range of downstream applications, such as visual question…

Existing codecs are designed to eliminate intrinsic redundancies to create a compact representation for compression. However, strong external priors from Multimodal Large Language Models (MLLMs) have not been explicitly explored in video…

Video large language models (video LLMs) excel at video comprehension but face significant computational inefficiency due to redundant video tokens. Existing token pruning methods offer solutions. However, approaches operating within the…

Although speculative decoding is widely used to accelerate Vision-Language Models (VLMs) inference, it faces severe performance collapse when applied to Video Large Language Models (Vid-LLMs). The draft model typically falls into the trap…

Multimodal Large Language Models (MLLMs) have achieved strong performance across many tasks, yet most systems remain limited to offline inference, requiring complete inputs before generating outputs. Recent streaming methods reduce latency…

Live streaming platforms require real-time monitoring and reaction to social signals, utilizing partial and asynchronous evidence from video, text, and audio. We propose StreamSense, a streaming detector that couples a lightweight streaming…

We introduce SlowFast-LLaVA-1.5 (abbreviated as SF-LLaVA-1.5), a family of video large language models (LLMs) offering a token-efficient solution for long-form video understanding. We incorporate the two-stream SlowFast mechanism into a…

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and describe complex visual content. However, applying these models…

The quadratic complexity of Multimodal Large Language Models (MLLMs) with respect to context length poses significant computational and memory challenges, hindering their real-world deployment. In the paper, we devise a…

Video large language models (Vid-LLMs), which excel in diverse video-language tasks, can be effectively constructed by adapting image-pretrained vision-language models (VLMs). However, this adaptation remains challenging, as it requires…

The long speech sequence has been troubling language models (LM) based TTS approaches in terms of modeling complexity and efficiency. This work proposes SoCodec, a semantic-ordered multi-stream speech codec, to address this issue. It…

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation.…

Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computational burden for deployment. Existing methods mainly prune…

In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a…

Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing. Unlike traditional task-specific models,…

Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Test-time adaptation (TTA) mitigates this issue by adjusting…

Transformer-based document cross-encoder rerankers are a central component of modern information retrieval systems. Despite their success, these models suffer from high computational costs due to processing long query-document sequences at…

Large language models (LLMs) increasingly rely on long-context modeling for tasks such as document understanding, code analysis, and multi-step reasoning. However, scaling context windows to the million-token level brings prohibitive…

Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality. While recent methods attempt to solve this by…