相关论文: VL-JEPA: Joint Embedding Predictive Architecture f…

Vision-Language Models (VLMs) have emerged as a promising approach to address the data scarcity challenge in robotics, enabling the development of generalizable visuomotor control policies. While models like OpenVLA showcase the potential…

Vision-Language Pre-training (VLP) methods based on object detection enjoy the rich knowledge of fine-grained object-text alignment but at the cost of computationally expensive inference. Recent Visual-Transformer (ViT)-based approaches…

Most Video-Large Language Models (Video-LLMs) adopt an encoder-decoder framework, where a vision encoder extracts frame-wise features for processing by a language model. However, this approach incurs high computational costs, introduces…

Vision-Language Models (VLMs) have demonstrated strong performance across various multimodal tasks, where position encoding plays a vital role in modeling both the sequential structure of textual information and the spatial structure of…

In this paper, we introduce $\text{EVL}_{\text{Gen}}$, a streamlined framework designed for the pre-training of visually conditioned language generation models with high computational demands, utilizing frozen pre-trained large language…

Single-cell foundation models learn by reconstructing masked gene expression, implicitly treating technical noise as signal. With dropout rates exceeding 90%, reconstruction objectives encourage models to encode measurement artifacts rather…

Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investigate this, we introduce ViLP, a benchmark featuring…

Learning efficient representations for decision-making policies is a challenge in imitation learning (IL). Current IL methods require expert demonstrations, which are expensive to collect. Additionally, they are not explicitly trained to…

Vision-Language-Action (VLA) models have emerged as a promising approach for enabling robots to follow language instructions and predict corresponding actions. However, current VLA models mainly rely on 2D visual inputs, neglecting the rich…

World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such models from distinct viewpoints of the same environment without any parameter sharing or…

We introduce MUSE-VL, a Unified Vision-Language Model through Semantic discrete Encoding for multimodal understanding and generation. Recently, the research community has begun exploring unified models for visual generation and…

Speculative decoding is a widely adopted technique for accelerating inference in large language models (LLMs), yet its application to vision-language models (VLMs) remains underexplored, with existing methods achieving only modest speedups…

Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. Existing efficiency approaches either merge redundant visual…

In this work, we introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for…

We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e.g., VQA, image captioning). GLIPv2 elegantly unifies…

Existing encoder-free vision-language models (VLMs) are rapidly narrowing the performance gap with their encoder-based counterparts, highlighting the promising potential for unified multimodal systems with structural simplicity and…

Most Vision Language Models (VLMs) directly map outputs from ViT encoders to the LLM via a lightweight projector. While effective, recent analysis suggests this architecture suffers from an alignment challenge: visual features remain…

In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream…

Recent studies have adapted generative Multimodal Large Language Models (MLLMs) into embedding extractors for vision tasks, typically through fine-tuning to produce universal representations. However, their performance on video remains…

In high energy physics, self-supervised learning (SSL) methods have the potential to aid in the creation of machine learning models without the need for labeled datasets for a variety of tasks, including those related to jets -- narrow…