相关论文: Gemini2: Generating Keyframe-Oriented Animated Tra…

Large language models (LLMs) are increasingly used to simulate human behavior in experimental settings, but they systematically diverge from human decisions in complex decision-making environments, where participants must anticipate others'…

Live animation of 2D characters has recently become a popular way for storytelling, and has potential application scenarios like tele-present agents or robots. As an extension of human-human communication, there is a need for augmenting the…

Table2Text systems generate textual output based on structured data utilizing machine learning. These systems are essential for fluent natural language interfaces in tools such as virtual assistants; however, left to generate freely these…

Generating large-scale multi-character interactions is a challenging and important task in character animation. Multi-character interactions involve not only natural interactive motions but also characters coordinated with each other for…

In many contexts, creating mappings for gestural interactions can form part of an artistic process. Creators seeking a mapping that is expressive, novel, and affords them a sense of authorship may not know how to program it up in a signal…

Physical computing infrastructure, data gathering, and algorithms have recently had significant advances to extract information from images and videos. The growth has been especially outstanding in image captioning and video captioning.…

People often create art by following an artistic workflow involving multiple stages that inform the overall design. If an artist wishes to modify an earlier decision, significant work may be required to propagate this new decision forward…

Despite recent progress, video generative models still struggle to animate static images into videos that portray delicate human actions, particularly when handling uncommon or novel actions whose training data are limited. In this paper,…

A common strategy to video understanding is to incorporate spatial and motion information by fusing features derived from RGB frames and optical flow. In this work, we introduce a new way to leverage semantic segmentation as an intermediate…

Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the…

Most state-of-the-art instance segmentation methods rely on large amounts of pixel-precise ground-truth annotations for training, which are expensive to create. Interactive segmentation networks help generate such annotations based on an…

Reconstructing human dynamic vision from brain activity is a challenging task with great scientific significance. Although prior video reconstruction methods have made substantial progress, they still suffer from several limitations,…

Technological progress has persistently shaped the dynamics of human-machine interactions in task execution. In response to the advancements in Generative AI, this paper outlines a detailed study plan that investigates various human-AI…

Dynamic graphs are common in real-world systems such as social media, recommender systems, and traffic networks. Existing dynamic graph models for link prediction often fall short in capturing the complexity of temporal evolution. They tend…

To integrate strategic, tactical and operational decisions, the two-stage optimization has been widely used to guide dynamic decision making. In this paper, we study the two-stage stochastic programming for complex systems with unknown…

Visual generative AI models often encounter challenges related to text-image alignment and reasoning limitations. This paper presents a novel method for selectively enhancing the signal at critical denoising steps, optimizing image…

This study investigates the integration of trustworthy prior reasoning knowledge from MLLMs into multimodal emotion recognition. We employ Gemini to generate fine-grained, modality-separable reasoning traces, which are injected as priors…

Human motion synthesis is a long-standing problem with various applications in digital twins and the Metaverse. However, modern deep learning based motion synthesis approaches barely consider the physical plausibility of synthesized motions…

Web page saliency prediction is a challenge problem in image transformation and computer vision. In this paper, we propose a new model combined with web page outline information to prediction people's interest region in web page. For each…

We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming honeypot evaluations take the form of coding tasks in Google's alignment research…