Related papers: AnyRefill: A Unified, Data-Efficient Framework for…
Retrieval-Augmented Generation (RAG) systems enhance text generation by incorporating external knowledge but often struggle when retrieving context across different text modalities due to semantic gaps. We introduce a generalized…
Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applications such as personalized advertising and virtual try-on.…
We present ASPIRO, an approach for structured data verbalisation into short template sentences in zero to few-shot settings. Unlike previous methods, our approach prompts large language models (LLMs) to directly produce entity-agnostic…
The existing Retrieval-Augmented Generation (RAG) systems face significant challenges in terms of cost and effectiveness. On one hand, they need to encode the lengthy retrieved contexts before responding to the input tasks, which imposes…
Vision language models (VLMs) have shown impressive capabilities across a variety of tasks, from logical reasoning to visual understanding. This opens the door to richer interaction with the world, for example robotic control. However, VLMs…
Retrieval-augmented generation (RAG) is now standard for knowledge-intensive LLM tasks, but most systems still treat every query as fresh, repeatedly re-retrieving long passages and re-reasoning from scratch, inflating tokens, latency, and…
Active object reconstruction using autonomous robots is gaining great interest. A primary goal in this task is to maximize the information of the object to be reconstructed, given limited on-board resources. Previous view planning methods…
Image reconstruction and image synthesis are important for handling incomplete multimodal imaging data, but existing methods require various task-specific models, complicating training and deployment workflows. We introduce Any2all, a…
Diffusion models have exhibit exceptional performance in text-to-image generation and editing. However, existing methods often face challenges when handling complex text prompts that involve multiple objects with multiple attributes and…
This work introduces a new multi-task, parameter-efficient language model (LM) tuning method that learns to transfer knowledge across different tasks via a mixture of soft prompts-small prefix embedding vectors pre-trained for different…
We present an end-to-end automated workflow that uses large-scale remote compute resources and an embedded GPU platform at the edge to enable AI/ML-accelerated real-time analysis of data collected for x-ray ptychography. Ptychography is a…
The Contrastive Language-Image Pretraining (CLIP) model has been widely used in various downstream vision tasks. The few-shot learning paradigm has been widely adopted to augment its capacity for these tasks. However, current paradigms may…
Individuals with intellectual disabilities often have difficulties in comprehending complex texts. While many text-to-image models prioritize aesthetics over accessibility, it is not clear how visual illustrations relate to text…
Embodied Everyday Task is a popular task in the embodied AI community, requiring agents to make a sequence of actions based on natural language instructions and visual observations. Traditional learning-based approaches face two challenges.…
Creative generation is the synthesis of new, surprising, and valuable samples that reflect user intent yet cannot be envisioned in advance. This task aims to extend human imagination, enabling the discovery of visual concepts that exist in…
We present Lunima-OmniLV (abbreviated as OmniLV), a universal multimodal multi-task framework for low-level vision that addresses over 100 sub-tasks across four major categories: image restoration, image enhancement, weak-semantic dense…
Image correction and rectangling are valuable tasks in practical photography systems such as smartphones. Recent remarkable advancements in deep learning have undeniably brought about substantial performance improvements in these fields.…
Retrieval-Augmented Generation (RAG) pipelines are central to applying large language models (LLMs) to proprietary or dynamic data. However, building effective RAG flows is complex, requiring careful selection among vector databases,…
Long-context large language models (LLMs), such as Gemini-2.5-Pro and Claude-Sonnet-4, are increasingly used to empower advanced AI systems, including retrieval-augmented generation (RAG) pipelines and autonomous agents. In these systems,…
Text simplification supports second language (L2) learning by providing comprehensible input, consistent with the Input Hypothesis. However, constructing personalized parallel corpora is costly, while existing large language model…