相关论文: MMInference: Accelerating Pre-filling for Long-Con…

Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of Vision Large Language Models (VLLMs). However, existing visual instruction tuning datasets include the following limitations: (1)…

In this paper, we introduce LightVLM, a simple but effective method that can be seamlessly deployed upon existing Vision-Language Models (VLMs) to greatly accelerate the inference process in a training-free manner. We divide the inference…

Deploying million-token Large Language Models (LLMs) is challenging because production workloads are highly heterogeneous, mixing short queries and long documents. This heterogeneity, combined with the quadratic complexity of attention,…

In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models (LLMs) significantly affects their performance in tasks demanding a high degree of context awareness, such as utilizing…

The advent of large vision-language models (LVLMs) has spurred research into their applications in multi-modal contexts, particularly in video understanding. Traditional VideoQA benchmarks, despite providing quantitative metrics, often fail…

Multimodal large language models (MLLMs) have garnered widespread attention due to their ability to understand multimodal input. However, their large parameter sizes and substantial computational demands severely hinder their practical…

Vision-Language Models (VLMs) are crucial for applications requiring integrated understanding textual and visual information. However, existing VLMs struggle with long videos due to computational inefficiency, memory limitations, and…

Handling lengthy context is crucial for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs) in applications such as processing high-resolution images or high frame rate videos. The rise in…

Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long context inputs, but this comes at the cost of increased computational resources and latency. Our research introduces a novel approach for the long…

To usher in the next round of client AI innovation, there is an urgent need to enable efficient, lossless inference of high-accuracy large language models (LLMs) and vision language models (VLMs), jointly referred to as xLMs, on client…

Multimodal large language models (MLLMs) deliver impressive vision-language reasoning but suffer steep inference latency because self-attention scales quadratically with sequence length and thousands of visual tokens contributed by…

Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or lengthy image-text…

Video sequences offer valuable temporal information, but existing large multimodal models (LMMs) fall short in understanding extremely long videos. Many works address this by reducing the number of visual tokens using visual resamplers.…

We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text. Powered by the iterative latent cross-attention of Perceiver, our framework scales with…

Hallucinations in large vision-language models (LVLMs) often stem from the model's sensitivity to image tokens during decoding, as evidenced by attention peaks observed when generating both real and hallucinated entities. To address this,…

Large Language Models (LLMs) exhibit pronounced memory-bound characteristics during inference due to High Bandwidth Memory (HBM) bandwidth constraints. In this paper, we propose an L2 Cache-oriented asynchronous KV Cache prefetching method…

Advanced autoregressive (AR) video generation models have improved visual fidelity and interactivity, but the quadratic complexity of attention remains a primary bottleneck for efficient deployment. While existing sparse attention solutions…

Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in short video understanding. However, understanding long-form videos still remains challenging for MLLMs. This paper proposes TimeSuite, a collection of new…

Most of the existing multi-modal models, hindered by their incapacity to adeptly manage interleaved image-and-text inputs in multi-image, multi-round dialogues, face substantial constraints in resource allocation for training and data…

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…