Related papers: Rethinking Visual Token Reduction in LVLMs Under C…

Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable inefficiencies: using excessive tokens leads to unnecessary…

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,…

Large Vision-Language Models (LVLMs) excel in cross-model tasks but experience performance declines in long-context reasoning due to overreliance on textual information and reduced visual dependency. In this study, we empirically analyze…

As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim…

Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-grounded dialogue, visual question answering, and scientific…

Visual token pruning aims to compress and prune redundant visual tokens which play a critical role in efficient inference with large vision-language models (LVLMs). However, most existing work estimates visual redundancy using a single…

Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration strategy, applying it at shallow decoder layers often causes…

High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadratic complexity while still generating excessive visual…

Recent years have witnessed remarkable advances in Large Vision-Language Models (LVLMs), which have achieved human-level performance across various complex vision-language tasks. Following LLaVA's paradigm, mainstream LVLMs typically employ…

Despite interpretability work analyzing VIT encoders and transformer activations, we don't yet understand why Multimodal Language Models (MLMs) struggle on perception-heavy tasks. We offer an under-studied perspective by examining how…

Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed rapid progress for learning cross-modal representations. Existing pre-training methods either directly concatenate image representation and text…

Transformer-based models have driven significant advancements in Multimodal Large Language Models (MLLMs), yet their computational costs surge drastically when scaling resolution, training data, and model parameters. A key bottleneck stems…

Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Learning (ViCO), a novel training algorithm…

Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive…

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

Multimodal learning plays a critical role in e-commerce recommendation platforms today, enabling accurate recommendations and product understanding. However, existing vision-language models, such as CLIP, face key challenges in e-commerce…

Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundancy. Because image…

In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and…

Multimodal Large Language Models (MLLMs) deliver strong vision-language performance but at high computational cost, driven by numerous visual tokens processed by the Vision Transformer (ViT) encoder. Existing token pruning strategies are…

Large Vision-Language Models (LVLMs) generate contextually relevant responses by jointly interpreting visual and textual inputs. However, our finding reveals they often mistakenly perceive text inputs lacking visual evidence as being part…