Related papers: ActionParty: Multi-Subject Action Binding in Gener…
In recent years, generative models have shown remarkable capabilities across diverse fields, including images, videos, language, and decision-making. By applying powerful generative models such as flow-based models to reinforcement…
We address the problem of accurate capture and expressive modelling of interactive behaviors happening between two persons in daily scenarios. Different from previous works which either only consider one person or focus on conversational…
In large-scale multi-agent systems, the large number of agents and complex game relationship cause great difficulty for policy learning. Therefore, simplifying the learning process is an important research issue. In many multi-agent…
Modern world models require costly and time-consuming collection of large video datasets with action demonstrations by people or by environment-specific agents. To simplify training, we focus on using many virtual environments for…
Action recognition and anticipation are key to the success of many computer vision applications. Existing methods can roughly be grouped into those that extract global, context-aware representations of the entire image or sequence, and…
Web agents based on large language models have demonstrated promising capability in automating web tasks. However, current web agents struggle to reason out sensible actions due to the limitations of predicting environment changes, and…
Object manipulation capabilities are essential skills that set apart embodied agents engaging with the world, especially in the realm of robotics. The ability to predict outcomes of interactions with objects is paramount in this setting.…
Are generative pre-trained transformer (GPT) models, trained only to predict the next token, implicitly learning a world model from which sequences are generated one token at a time? We address this question by deriving a causal…
Custom Storyboard Generation (CSG) aims to produce high-quality, multi-character consistent storytelling. Current approaches based on static diffusion models, whether used in a one-shot manner or within multi-agent frameworks, face three…
Autoregressive video generation aims at real-time, open-ended synthesis. Yet, cinematic storytelling is not merely the endless extension of a single scene; it requires progressing through evolving events, viewpoint shifts, and discrete shot…
We present visual action prompts, a unified action representation for action-to-video generation of complex high-DoF interactions while maintaining transferable visual dynamics across domains. Action-driven video generation faces a…
This paper proposes a novel problem: vision-based perception to learn and predict the collective dynamics of multi-agent systems, specifically focusing on interaction strength and convergence time. Multi-agent systems are defined as…
We introduce PlayerOne, the first egocentric realistic world simulator, facilitating immersive and unrestricted exploration within vividly dynamic environments. Given an egocentric scene image from the user, PlayerOne can accurately…
Recent interactive video world model methods generate scene evolution conditioned on user instructions. Although they achieve impressive results, two key limitations remain. First, they exhibit motion drift in complex environments with…
Video generative models pre-trained on large-scale internet datasets have achieved remarkable success, excelling at producing realistic synthetic videos. However, they often generate clips based on static prompts (e.g., text or images),…
Active Inference is an emerging framework providing a quantitative account of behavioral processes in neuroscience and a principled approach to decision-making under uncertainty. Its application to agency problems is natural, offering an…
Subject-driven image generation is increasingly expected to support fine-grained control over multiple entities within a single image. In multi-reference workflows, users may provide several subject images, a background reference, and long,…
Models that can simulate how environments change in response to actions can be used by agents to plan and act efficiently. We improve on previous environment simulators from high-dimensional pixel observations by introducing recurrent…
Action Detection is a complex task that aims to detect and classify human actions in video clips. Typically, it has been addressed by processing fine-grained features extracted from a video classification backbone. Recently, thanks to the…
Recent advancements in predictive models have demonstrated exceptional capabilities in predicting the future state of objects and scenes. However, the lack of categorization based on inherent characteristics continues to hinder the progress…