Imagen de Portada

Improving World Models using Deep Supervision with Linear Probes

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Zahorodnii, Andrii
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Project Jenkins: Turning Monkey Neural Data into Robotic Arm Movement, and Back
por: Zahorodnii, Andrii, et al.
Publicado: (2025)

Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models
por: Balashov, Andrii
Publicado: (2025)

Understanding and Improving Hyperbolic Deep Reinforcement Learning
por: Klein, Timo, et al.
Publicado: (2025)

Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift
por: Pandey, Amit
Publicado: (2025)

World Modelling Improves Language Model Agents
por: Guo, Shangmin, et al.
Publicado: (2025)

Transformers Linearly Represent Highly Structured World Models
por: Kniazev, Roman, et al.
Publicado: (2026)

Deep Minds and Shallow Probes
por: Lee, Su Hyeong, et al.
Publicado: (2026)

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

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

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

Probing the Impact of Scale on Data-Efficient, Generalist Transformer World Models for Atari
por: Kim, Jooyeon
Publicado: (2026)

What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
por: Vafa, Keyon, et al.
Publicado: (2025)

Improving Transformer World Models for Data-Efficient RL
por: Dedieu, Antoine, et al.
Publicado: (2025)

Masked Generative Priors Improve World Models Sequence Modelling Capabilities
por: Meo, Cristian, et al.
Publicado: (2024)

Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision
por: Fang, Jiayi
Publicado: (2026)

Improving Token-Based World Models with Parallel Observation Prediction
por: Cohen, Lior, et al.
Publicado: (2024)

Multimodal Deep Generative Model for Semi-Supervised Learning under Class Imbalance
por: Yoon, Heegeon, et al.
Publicado: (2026)

Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation
por: Radharapu, Bhaktipriya, et al.
Publicado: (2025)

Deep SPI: Safe Policy Improvement via World Models
por: Delgrange, Florent, et al.
Publicado: (2025)

Improving User Behavior Prediction: Leveraging Annotator Metadata in Supervised Machine Learning Models
por: Ng, Lynnette Hui Xian, et al.
Publicado: (2025)

WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making
por: Levy, Guillaume, et al.
Publicado: (2025)

Future-as-Label: Scalable Supervision from Real-World Outcomes
por: Turtel, Benjamin, et al.
Publicado: (2026)

Breaking the Reclustering Barrier in Centroid-based Deep Clustering
por: Miklautz, Lukas, et al.
Publicado: (2024)

Supervised Dynamic Dimension Reduction with Deep Neural Network
por: Luo, Zhanye, et al.
Publicado: (2025)

World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
por: Liu, Yuejiang, et al.
Publicado: (2026)

A Rubric-Supervised Critic from Sparse Real-World Outcomes
por: Wang, Xingyao, et al.
Publicado: (2026)

Large Language Models for Sequential Decision-Making: Improving In-Context Learning via Supervised Fine-Tuning
por: Zhang, Minmin, et al.
Publicado: (2026)

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression
por: Shukla, Megh, et al.
Publicado: (2025)

Meta-World+: An Improved, Standardized, RL Benchmark
por: McLean, Reginald, et al.
Publicado: (2025)

Integrating Random Forests and Generalized Linear Models for Improved Accuracy and Interpretability
por: Agarwal, Abhineet, et al.
Publicado: (2023)

Self-Improving World Modelling with Latent Actions
por: Qiu, Yifu, et al.
Publicado: (2026)

Generalised Linear Models in Deep Bayesian RL with Learnable Basis Functions
por: You, Jingyang, et al.
Publicado: (2025)

Real-World Robot Control by Deep Active Inference With a Temporally Hierarchical World Model
por: Fujii, Kentaro, et al.
Publicado: (2025)

DeepCell: Self-Supervised Multiview Fusion for Circuit Representation Learning
por: Shi, Zhengyuan, et al.
Publicado: (2025)

Enhancing In-context Learning via Linear Probe Calibration
por: Abbas, Momin, et al.
Publicado: (2024)

Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains
por: Lee, Kyungeun, et al.
Publicado: (2024)

How to Provably Improve Return Conditioned Supervised Learning?
por: Liu, Zhishuai, et al.
Publicado: (2025)

Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation
por: Yokozawa, Riko, et al.
Publicado: (2025)

Learning Distinguishable Representations in Deep Q-Networks for Linear Transfer
por: Sathish, Sooraj, et al.
Publicado: (2025)

Red-teaming Activation Probes using Prompted LLMs
por: Blandfort, Phil, et al.
Publicado: (2025)