Related papers: Overcoming Visual Clutter in Vision Language Actio…

Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the…

Vision-Language-Action (VLA) models, particularly diffusion-based architectures, demonstrate transformative potential for embodied intelligence but are severely hampered by high computational and memory demands stemming from extensive…

Dataset distillation (DD) condenses large datasets into compact yet informative substitutes, preserving performance comparable to the original dataset while reducing storage, transmission costs, and computational consumption. However,…

The performance of robotic imitation learning is fundamentally limited by data quality and training strategies. Prevalent sampling strategies on RLBench suffer from severe keyframe redundancy and imbalanced temporal distribution, leading to…

Vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs, resulting in remarkable generalization across several data distributions. However, in several cases, their expensive training and data…

Knowledge distillation has made remarkable achievements in model compression. However, most existing methods require the original training data, which is usually unavailable due to privacy and security issues. In this paper, we propose a…

Knowledge distillation (KD), a technique widely employed in computer vision, has emerged as a de facto standard for improving the performance of small neural networks. However, prevailing KD-based approaches in video tasks primarily focus…

Large Vision-Language Models (LVLMs) are susceptible to object hallucinations, an issue in which their generated text contains non-existent objects, greatly limiting their reliability and practicality. Current approaches often rely on the…

Since visual perception can give rich information beyond text descriptions for world understanding, there has been increasing interest in leveraging visual grounding for language learning. Recently, vokenization (Tan and Bansal, 2020) has…

In this paper, we tackle a new problem: how to transfer knowledge from the pre-trained cumbersome yet well-performed CNN-based model to learn a compact Vision Transformer (ViT)-based model while maintaining its learning capacity? Due to the…

Fine-grained image classification, particularly in zero/few-shot scenarios, presents a significant challenge for vision-language models (VLMs), such as CLIP. These models often struggle with the nuanced task of distinguishing between…

Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM…

Solving complex visual tasks such as "Who invented the musical instrument on the right?" involves a composition of skills: understanding space, recognizing instruments, and also retrieving prior knowledge. Recent work shows promise by…

The reliance on language in Vision-Language-Action (VLA) models introduces ambiguity, cognitive overhead, and difficulties in precise object identification and sequential task execution, particularly in environments with multiple visually…

Recently, linear complexity sequence modeling networks have achieved modeling capabilities similar to Vision Transformers on a variety of computer vision tasks, while using fewer FLOPs and less memory. However, their advantage in terms of…

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…

Contrastive language-image pretraining (CLIP) links vision and language modalities into a unified embedding space, yielding the tremendous potential for vision-language (VL) tasks. While early concurrent works have begun to study this…

Vision-Language-Action (VLA) models improve action generation by conditioning policies on rich vision-language information. However, current auto-regressive policies are constrained by three bottlenecks: (1) architectural bias drives models…

Generative Adversarial Networks (GANs) rely heavily on large-scale training data for training high-quality image generation models. With limited training data, the GAN discriminator often suffers from severe overfitting which directly leads…

In this paper, we propose a novel approach for solving the Visual Question Answering (VQA) task in autonomous driving by integrating Vision-Language Models (VLMs) with continual learning. In autonomous driving, VQA plays a vital role in…