Related papers: Beyond Attention Magnitude: Leveraging Inter-layer…
Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous datasets. However, approaches to supervising VLAs with latent actions are fragmented and…
Vision-language models (VLMs) typically encode substantially more visual tokens than text tokens, resulting in significant token redundancy. Pruning uninformative visual tokens is therefore crucial for improving computational efficiency,…
Vision-Language-Action (VLA) models have demonstrated remarkable generalization capabilities in robotic manipulation tasks, yet their substantial computational overhead remains a critical obstacle to real-world deployment. Improving…
Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence, yet their outputs remain prone to hallucination-plausible text misaligned with visual inputs. Existing alignment approaches often rely on…
Vision-language models (VLMs) are commonly trained by directly inserting image tokens from a pretrained vision encoder into the text stream of a language model. This allows text and image information to fully attend to one another within…
Recent large-scale Vision Language Action (VLA) models have shown superior performance in robotic manipulation tasks guided by natural language. However, current VLA models suffer from two drawbacks: (i) generation of massive tokens leading…
Current research on Vision-Language-Action (VLA) models predominantly focuses on enhancing generalization through established reasoning techniques. While effective, these improvements invariably increase computational complexity and…
Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…
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…
Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…
Despite the success of vision transformers (ViTs), they still suffer from significant drops in accuracy in the presence of common corruptions, such as noise or blur. Interestingly, we observe that the attention mechanism of ViTs tends to…
Understanding how Large Language Models (LLMs) process information from prompts remains a significant challenge. To shed light on this "black box," attention visualization techniques have been developed to capture neuron-level perceptions…
Attention models are widely used in Vision-language (V-L) tasks to perform the visual-textual correlation. Humans perform such a correlation with a strong linguistic understanding of the visual world. However, even the best performing…
Modern multimodal large language models (MLLMs) adopt a unified self-attention design that processes visual and textual tokens at every Transformer layer, incurring substantial computational overhead. In this work, we revisit the necessity…
Vision-Language-Action (VLA) models process visual inputs independently at each timestep, discarding valuable temporal information inherent in robotic manipulation tasks. This frame-by-frame processing makes models vulnerable to visual…
Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for generalist robotic control. Built upon vision-language model (VLM) architectures, VLAs predict actions conditioned on visual observations and language…
Vision-Language-Action (VLA) models pretrained on large-scale multimodal datasets have emerged as powerful foundations for robotic perception and control. However, their massive scale, often billions of parameters, poses significant…
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…
Token reduction is an effective way to accelerate long-video vision-language models (VLMs), but most existing methods are designed for dense Transformers and do not directly account for hybrid architectures that interleave attention with…
Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we…