Related papers: Delta-LLaVA: Base-then-Specialize Alignment for To…

Existing aerial Vision-Language Navigation (VLN) methods predominantly adopt a detection-and-planning pipeline, which converts open-vocabulary detections into discrete textual scene graphs. These approaches are plagued by inadequate spatial…

Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, which hurts tasks like open-vocabulary semantic segmentation; and (2) high token counts for…

Vision-Language Models (VLMs) have demonstrated strong capabilities in multimodal understanding and generation tasks. However, their application to long video understanding remains hindered by the quadratic complexity of standard attention…

Multimodal large language models (MLLMs) have demonstrated impressive performance in various vision-language (VL) tasks, but their expensive computations still limit the real-world application. To address this issue, recent efforts aim to…

We introduce Long-VITA, a simple yet effective large multi-modal model for long-context visual-language understanding tasks. It is adept at concurrently processing and analyzing modalities of image, video, and text over 4K frames or 1M…

Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either before the LLM, limiting generality due to diverse…

Vision-Language-Action (VLA) models have demonstrated strong multi-modal reasoning capabilities, enabling direct action generation from visual perception and language instructions in an end-to-end manner. However, their substantial…

Large language models are built on top of a transformer-based architecture to process textual inputs. For example, the LLaMA stands out among many open-source implementations. Can the same transformer be used to process 2D images? In this…

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…

Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies. However, current VLAs are mostly trained on large-scale image-text-action data and remain limited in two key ways:…

Multimodal Large Language Models (MLLMs) mainly fall into two architectures, each involving a trade-off between training and inference efficiency: embedding space alignment (e.g., LLaVA-1.5) is inefficient during inference, while…

3D vision-language grounding (3D-VL) is an emerging field that aims to connect the 3D physical world with natural language, which is crucial for achieving embodied intelligence. Current 3D-VL models rely heavily on sophisticated modules,…

The Large Vision-Language Model (LVLM) integrates computer vision and natural language processing techniques, offering substantial application potential. However, these models demand extensive resources during inference. Adaptive attention…

This paper introduces Chain-of-Sight, a vision-language bridge module that accelerates the pre-training of Multimodal Large Language Models (MLLMs). Our approach employs a sequence of visual resamplers that capture visual details at various…

Pre-trained language models (PLMs) have played an increasing role in multimedia research. In terms of vision-language (VL) tasks, they often serve as a language encoder and still require an additional fusion network for VL reasoning,…

Vision-Language-Action (VLA) models built on pretrained Vision-Language Models (VLMs) show strong potential but are limited in practicality due to their large parameter counts. To mitigate this issue, using a lightweight VLM has been…

Multimodal language models (MLMs) still face challenges in fundamental visual perception tasks where specialized models excel. Tasks requiring reasoning about 3D structures benefit from depth estimation, and reasoning about 2D object…

While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound reasoning capabilities inherited from their base…

Vision Language Models (VLMs) excel at identifying and describing objects but often fail at spatial reasoning. We study why VLMs, such as LLaVA, underutilize spatial cues despite having positional encodings and spatially rich vision encoder…

End-to-end autonomous driving requires models to understand traffic scenes, infer driving intent, and generate executable motion plans. Recent vision-language-action (VLA) models inherit semantic priors from large-scale vision-language…