Related papers: Text or Pixels? It Takes Half: On the Token Effici…

In this paper, we introduce LDGen, a novel method for integrating large language models (LLMs) into existing text-to-image diffusion models while minimizing computational demands. Traditional text encoders, such as CLIP and T5, exhibit…

Transforming a large language model (LLM) into a Vision-Language Model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP…

Although Large Vision Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, their scalability and deployment are constrained by massive computational requirements. In particular, the massive amount of…

Multimodal large language models (MLLMs) project visual tokens into the embedding space of language models, yet the internal structuring and processing of visual semantics remain poorly understood. In this work, we introduce a two-fold…

In language processing, transformers benefit greatly from text being condensed. This is achieved through a larger vocabulary that captures word fragments instead of plain characters. This is often done with Byte Pair Encoding. In the…

Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in comprehending complex visual content. However, the mechanisms underlying how VLMs process visual information remain largely unexplored. In this paper, we…

Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. However, processing long sequences of visual tokens extracted…

Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large…

Subword tokenization requires balancing computational efficiency and vocabulary coverage, which often leads to suboptimal performance on languages and scripts not prioritized during training. We propose to augment pretrained language models…

Recently, Referring Image Segmentation (RIS) frameworks that pair the Multimodal Large Language Model (MLLM) with the Segment Anything Model (SAM) have achieved impressive results. However, adapting MLLM to segmentation is computationally…

Most multimodal large language models (MLLMs) treat visual tokens as "a sequence of text", integrating them with text tokens into a large language model (LLM). However, a great quantity of visual tokens significantly increases the demand…

Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning…

Most large multimodal models (LMMs) are implemented by feeding visual tokens as a sequence into the first layer of a large language model (LLM). The resulting architecture is simple but significantly increases computation and memory costs,…

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the large number of visual tokens, particularly in…

Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off:…

Large language models (LLMs) face significant token efficiency bottlenecks in code generation and logical reasoning tasks, a challenge that directly impacts inference cost and model interpretability. This paper proposes a formal framework…

Long-context reasoning has significantly empowered large language models (LLMs) to tackle complex tasks, yet it introduces severe efficiency bottlenecks due to the computational complexity. Existing efficient approaches often rely on…

Large Multimodal Models (LMMs) are powerful tools that are capable of reasoning and understanding multimodal information beyond text and language. Despite their entrenched impact, the development of LMMs is hindered by the higher…

Amidst the advancements in image-based Large Vision-Language Models (image-LVLM), the transition to video-based models (video-LVLM) is hindered by the limited availability of quality video data. This paper addresses the challenge by…

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…