相关论文: Multimodal Procedural Planning via Dual Text-Image…

High-level autonomy requires discrete and continuous reasoning to decide both what actions to take and how to execute them. Integrated Task and Motion Planning (TMP) algorithms solve these hybrid problems jointly to consider constraints…

Deploying large multimodal language models at scale is constrained by token-based inference costs, yet the cost-performance behavior of visual prompting strategies remains poorly characterized. We introduce Image Prompt Packaging (IPPg), a…

Vision-language models (VLMs) have exhibited remarkable generalization capabilities, and prompt learning for VLMs has attracted great attention for the ability to adapt pre-trained VLMs to specific downstream tasks. However, existing…

CLIP is a seminal multimodal model that maps images and text into a shared representation space through contrastive learning on billions of image-caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate…

We introduce Meta-Reasoning Prompting (MRP), a novel and efficient system prompting method for large language models (LLMs) inspired by human meta-reasoning. Traditional in-context learning-based reasoning techniques, such as…

Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question…

Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory…

Text-to-image generative models excel in creating images from text but struggle with ensuring alignment and consistency between outputs and prompts. This paper introduces TextMatch, a novel framework that leverages multimodal optimization…

Vision-Language Models (VLMs) often suffer from hallucination, partly due to challenges in aligning multimodal information. We propose Prompt-in-Image, a simple method that embeds textual instructions directly into images. This removes the…

Traditional ML models utilize controlled approximations during high loads, employing faster, but less accurate models in a process called accuracy scaling. However, this method is less effective for generative text-to-image models due to…

Aligning text-to-image generation with user intent remains challenging, as users frequently provide ambiguous inputs and struggle with model idiosyncrasies. We propose Adaptive Prompt Elicitation (APE), a technique that adaptively poses…

With the emergence of large pre-trained vison-language model like CLIP, transferable representations can be adapted to a wide range of downstream tasks via prompt tuning. Prompt tuning tries to probe the beneficial information for…

The rapid advancement of generative AI has democratized access to powerful tools such as Text-to-Image models. However, to generate high-quality images, users must still craft detailed prompts specifying scene, style, and context-often…

Image restoration, which aims to retrieve and enhance degraded images, is fundamental across a wide range of applications. While conventional deep learning approaches have notably improved the image quality across various tasks, they still…

A critical challenge in multi-agent reinforcement learning(MARL) is for multiple agents to efficiently accomplish complex, long-horizon tasks. The agents often have difficulties in cooperating on common goals, dividing complex tasks, and…

Large language models (LLMs) demonstrate impressive performance on a wide variety of tasks, but they often struggle with tasks that require multi-step reasoning or goal-directed planning. Both cognitive neuroscience and reinforcement…

This paper presents instruct-imagen, a model that tackles heterogeneous image generation tasks and generalizes across unseen tasks. We introduce *multi-modal instruction* for image generation, a task representation articulating a range of…

Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights. While extending prompts to both vision and text encoders across multiple…

Bimanual robotic manipulation provides significant versatility, but also presents an inherent challenge due to the complexity involved in the spatial and temporal coordination between two hands. Existing works predominantly focus on…

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex…