Related Experiment Video
Updated: Jun 2, 2026
07:14
Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
Published on: December 23, 2025
SocialGen: Modeling Multi-Human Social Interaction with Language Models
Heng Yu1, Juze Zhang1, Changan Chen1
1Stanford University.
Proceedings. International Conference on 3D Vision
|June 1, 2026
Summary
SocialGen is the first unified motion-language model for multi-human interactions. It uses a novel representation and the SocialX dataset to achieve state-of-the-art results in social behavior modeling.
Area of Science:
- Computer Science
- Artificial Intelligence
- Human-Computer Interaction
Background:
- Human interactions are complex and fundamental to many applications.
- Existing models often struggle with interactions involving more than two people.
- Bridging the gap between human motion and language understanding is crucial for social behavior modeling.
Purpose of the Study:
- Introduce SocialGen, a unified motion-language model for multi-human interactions.
- Develop a novel social motion representation for arbitrary numbers of individuals.
- Establish a comprehensive benchmark and dataset for multi-human interaction tasks.
Main Methods:
- Proposed a novel social motion representation supporting tokenization of multi-person motions.
- Aligned motion representations with the language space to leverage linguistic knowledge.
- Curated the SocialX dataset, a comprehensive multi-human interaction dataset with textual annotations.
Main Results:
- Achieved state-of-the-art performance on motion-language tasks involving social interactions.
- Demonstrated the effectiveness of the unified motion-language approach for multi-human modeling.
- Established a new benchmark for evaluating multi-human interaction models.
Conclusions:
- SocialGen advances the field of social behavior modeling by enabling the understanding of interactions among multiple individuals.
- The proposed motion-language alignment and SocialX dataset provide a strong foundation for future research.
- This work sets a new standard for multi-human interaction modeling and its applications.
Related Concept Videos
01:12Modeling and Similitude
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
01:26Modeling in Therapy
Modeling, a key technique in therapy, uses observational learning to help clients acquire and practice new skills by watching therapists demonstrate desired behaviors. This approach, rooted in Albert Bandura's concept of vicarious learning, plays a significant role in therapeutic interventions for various psychological conditions, including social anxiety, ADHD, and depression.
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in situations...
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in situations...
01:28Automatic Processing and Automatic Social Behavior
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
01:27Language and Cognition
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
02:16Stereotype Content Model
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence categorization, a person will feel...
01:30Social Foundations of Self IV: Self in Digital Communication
Since the early 2000s, computer-mediated communication (CMC) has grown rapidly, playing a crucial role in self-development. A key distinction between CMC and real-life interactions is the lack of a physically present partner. This absence makes non-verbal cues such as facial expressions, body language, and paralinguistic signals unavailable in CMC platforms like email, instant messaging, or social media. The lack of these cues can create ambiguity and complicate how feedback is interpreted.The...