Cover Image

Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Fang, Jiayi
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Impact of Semantic Pairs on Self-Supervised Representation Learning
by: Alkhalefi, Mohammad, et al.
Published: (2025)

Emergent Representations of Program Semantics in Language Models Trained on Programs
by: Jin, Charles, et al.
Published: (2023)

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
by: Li, Kenneth, et al.
Published: (2022)

Uncovering Emergent Physics Representations Learned In-Context by Large Language Models
by: Song, Yeongwoo, et al.
Published: (2025)

Probing the Latent World: Emergent Discrete Symbols and Physical Structure in Latent Representations
by: ming, Liu hung
Published: (2026)

Convergent Linear Representations of Emergent Misalignment
by: Soligo, Anna, et al.
Published: (2025)

Emergent Semantic Role Understanding in Language Models
by: Griffiths, Carla, et al.
Published: (2026)

Analyzing the Role of Semantic Representations in the Era of Large Language Models
by: Jin, Zhijing, et al.
Published: (2024)

Semantic World Models
by: Berg, Jacob, et al.
Published: (2025)

Context-Enhanced Multi-View Trajectory Representation Learning: Bridging the Gap through Self-Supervised Models
by: Qian, Tangwen, et al.
Published: (2024)

Cross-Model Semantics in Representation Learning
by: Nikooroo, Saleh, et al.
Published: (2025)

Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model
by: Wu, Minghao, et al.
Published: (2026)

Quantifying Representation Reliability in Self-Supervised Learning Models
by: Park, Young-Jin, et al.
Published: (2023)

ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood
by: Wang, Ruoyu, et al.
Published: (2024)

KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data
by: Tang, Grace, et al.
Published: (2024)

Improving World Models using Deep Supervision with Linear Probes
by: Zahorodnii, Andrii
Published: (2025)

Towards Effective and Efficient Graph Alignment without Supervision
by: Chen, Songyang, et al.
Published: (2026)

PRISM: Purified Representation and Integrated Semantic Modeling for Generative Sequential Recommendation
by: Fang, Dengzhao, et al.
Published: (2026)

Simple, Good, Fast: Self-Supervised World Models Free of Baggage
by: Robine, Jan, et al.
Published: (2025)

Learning To Explore With Predictive World Model Via Self-Supervised Learning
by: Santana, Alana, et al.
Published: (2025)

Learning Latent Dynamic Robust Representations for World Models
by: Sun, Ruixiang, et al.
Published: (2024)

Neuro-symbolic Weak Supervision: Theory and Semantics
by: Upreti, Nijesh, et al.
Published: (2025)

Model Organisms for Emergent Misalignment
by: Turner, Edward, et al.
Published: (2025)

Understanding Distributed Representations of Concepts in Deep Neural Networks without Supervision
by: Chang, Wonjoon, et al.
Published: (2023)

Emergent Language Symbolic Autoencoder (ELSA) with Weak Supervision to Model Hierarchical Brain Networks
by: Latheef, Ammar Ahmed Pallikonda, et al.
Published: (2024)

Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training
by: Dave, Vedant, et al.
Published: (2024)

Mastering Diverse Domains through World Models
by: Hafner, Danijar, et al.
Published: (2023)

Understanding Representation Learnability of Nonlinear Self-Supervised Learning
by: Yang, Ruofeng, et al.
Published: (2024)

Data-Driven Self-Supervised Graph Representation Learning
by: Samy, Ahmed E., et al.
Published: (2024)

Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs
by: Zhou, Yifan, et al.
Published: (2025)

Better Decisions through the Right Causal World Model
by: Dillies, Elisabeth, et al.
Published: (2025)

Convergent World Representations and Divergent Tasks
by: Park, Core Francisco
Published: (2026)

Towards Unraveling and Improving Generalization in World Models
by: Fang, Qiaoyi, et al.
Published: (2024)

Unlocking Emergent Modularity in Large Language Models
by: Qiu, Zihan, et al.
Published: (2023)

Multimodal Representation Learning Conditioned on Semantic Relations
by: Qiao, Yang, et al.
Published: (2025)

R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
by: Morihira, Naoki, et al.
Published: (2026)

Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision
by: Cao, Shengcao, et al.
Published: (2024)

Fast and Featureless Node Representation Learning with Partial Pairwise Supervision
by: Chakraborty, Sujan, et al.
Published: (2026)

Self-Supervised Representation Learning for Geospatial Objects: A Survey
by: Chen, Yile, et al.
Published: (2024)

Self-Supervised Learning of Disentangled Representations for Multivariate Time-Series
by: Chang, Ching, et al.
Published: (2024)