相关论文: OmniAlpha: Aligning Transparency-Aware Generation …

This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering)…

Multi-agent reinforcement learning shines as the pinnacle of multi-agent systems, conquering intricate real-world challenges, fostering collaboration and coordination among agents, and unleashing the potential for intelligent…

Existing unified methods typically treat multi-degradation image restoration as a multi-task learning problem. Despite performing effectively compared to single degradation restoration methods, they overlook the utilization of commonalities…

As generative models expand the possibilities of visual content creation, layered image synthesis has emerged as a promising direction for controllable and creative editing. However, existing methods struggle to fully realize this…

OmniGraph, a novel representation to support a range of NLP classification tasks, integrates lexical items, syntactic dependencies and frame semantic parses into graphs. Feature engineering is folded into the learning through convolution…

Current Vision-Language-Action (VLA) models typically treat the deepest representation of a vision-language backbone as universally optimal for action prediction. However, robotic manipulation is composed of many frequent closed-loop…

Recently, how to achieve precise image editing has attracted increasing attention, especially given the remarkable success of text-to-image generation models. To unify various spatial-aware image editing abilities into one framework, we…

Developing Audio-Visual Large Language Models (AV-LLMs) for unified scene understanding is pivotal in multimodal intelligence. While instruction tuning enables pre-trained models with multi-task abilities, we observe that conventional…

Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training. Such a setting severely limits their scalability in real-world…

Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration. Existing evaluations either treat the two abilities in isolation or overlook tasks that…

Unsupervised Multiplex Graph Learning (UMGL) aims to learn node representations on various edge types without manual labeling. However, existing research overlooks a key factor: the reliability of the graph structure. Real-world data often…

A generalist robot should perform effectively across various environments. However, most existing approaches heavily rely on scaling action-annotated data to enhance their capabilities. Consequently, they are often limited to single…

Learning features from massive unlabelled data is a vast prevalent topic for high-level tasks in many machine learning applications. The recent great improvements on benchmark data sets achieved by increasingly complex unsupervised learning…

Data-driven machine learning approaches have recently been proposed to facilitate wireless network optimization by learning latent knowledge from historical optimization instances. However, existing methods do not well handle the topology…

Transformers have captured growing attention in computer vision, thanks to its large capacity and global processing capabilities. However, transformers are data hungry, and their ability to generalize is constrained compared to…

Reinforcement learning has emerged as a promising paradigm for aligning diffusion and flow-matching models with human preferences, yet practitioners face fragmented codebases, model-specific implementations, and engineering complexity. We…

The proliferation of synthetic facial imagery has intensified the need for robust Open-World DeepFake Attribution (OW-DFA), which aims to attribute both known and unknown forgeries using labeled data for known types and unlabeled data…

Retrieval-Augmented Generation (RAG) delivers substantial value in knowledge-intensive applications. However, its generated responses often lack transparent reasoning paths that trace back to source evidence from retrieved documents. This…

We present a method that tackles the challenge of predicting color and depth behind the visible content of an image. Our approach aims at building up a Layered Depth Image (LDI) from a single RGB input, which is an efficient representation…

One-class recognition is traditionally approached either as a representation learning problem or a feature modeling problem. In this work, we argue that both of these approaches have their own limitations; and a more effective solution can…