Imagen de Portada

MetaOthello: A Controlled Study of Multiple World Models in Transformers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chawla, Aviral, Hall, Galen, Lovato, Juniper
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Automatically Finding Rule-Based Neurons in OthelloGPT
por: Singh, Aditya, et al.
Publicado: (2025)

Emergent Stack Representations in Modeling Counter Languages Using Transformers
por: Tiwari, Utkarsh, et al.
Publicado: (2025)

Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT
por: He, Zhengfu, et al.
Publicado: (2024)

Provable Generalization in Overparameterized Neural Nets
por: Dhingra, Aviral
Publicado: (2025)

A Comparative Study of CNN, ResNet, and Vision Transformers for Multi-Classification of Chest Diseases
por: Jain, Ananya, et al.
Publicado: (2024)

Gradient Descent Efficiency Index
por: Dhingra, Aviral
Publicado: (2024)

MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games
por: Wu, Ti-Rong, et al.
Publicado: (2023)

Dimension-Free Bounds for Generalized First-Order Methods via Gaussian Coupling
por: Reeves, Galen
Publicado: (2025)

AnyLoss: Transforming Classification Metrics into Loss Functions
por: Han, Doheon, et al.
Publicado: (2024)

phepy: Visual Benchmarks and Improvements for Out-of-Distribution Detectors
por: Tyree, Juniper, et al.
Publicado: (2025)

A Formal Framework for Assessing and Mitigating Emergent Security Risks in Generative AI Models: Bridging Theory and Dynamic Risk Mitigation
por: Srivastava, Aviral, et al.
Publicado: (2024)

Human-AI Co-Mentorship in Project-Based Learning: A Case Study in Financial Forecasting
por: Chawla, Freyaa, et al.
Publicado: (2026)

Rapid Bayesian identification of sparse nonlinear dynamics from scarce and noisy data
por: Fung, Lloyd, et al.
Publicado: (2024)

Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
por: Wang, Zhi, et al.
Publicado: (2024)

Unfamiliar Finetuning Examples Control How Language Models Hallucinate
por: Kang, Katie, et al.
Publicado: (2024)

Digi-Q: Learning Q-Value Functions for Training Device-Control Agents
por: Bai, Hao, et al.
Publicado: (2025)

TabPFN Through The Looking Glass: An interpretability study of TabPFN and its internal representations
por: Gupta, Aviral, et al.
Publicado: (2026)

BIRD: Behavior Induction via Representation-structure Distillation
por: Pogoncheff, Galen, et al.
Publicado: (2025)

Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance
por: Nakamoto, Mitsuhiko, et al.
Publicado: (2024)

Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models
por: Le, Khiem, et al.
Publicado: (2026)

Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
por: Qian, Fuyuan, et al.
Publicado: (2026)

Contextual Latent World Models for Offline Meta Reinforcement Learning
por: Nakheai, Mohammadreza, et al.
Publicado: (2026)

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
por: Rimon, Zohar, et al.
Publicado: (2024)

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
por: Bai, Hao, et al.
Publicado: (2024)

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
por: Snell, Charlie, et al.
Publicado: (2024)

Information-Theoretic Proofs for Diffusion Sampling
por: Reeves, Galen, et al.
Publicado: (2025)

What Does Flow Matching Bring To TD Learning?
por: Agrawalla, Bhavya, et al.
Publicado: (2026)

Generative Verifiers: Reward Modeling as Next-Token Prediction
por: Zhang, Lunjun, et al.
Publicado: (2024)

TransDreamer: Reinforcement Learning with Transformer World Models
por: Chen, Chang, et al.
Publicado: (2022)

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
por: Wu, Ian, et al.
Publicado: (2026)

SPARTAN: A Sparse Transformer World Model Attending to What Matters
por: Lei, Anson, et al.
Publicado: (2024)

Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs
por: Li, Chenyang, et al.
Publicado: (2024)

Meta-learning Representations for Learning from Multiple Annotators
por: Kumagai, Atsutoshi, et al.
Publicado: (2025)

Differentially-Private Data Synthetisation for Efficient Re-Identification Risk Control
por: Carvalho, Tânia, et al.
Publicado: (2022)

Discrete Codebook World Models for Continuous Control
por: Scannell, Aidan, et al.
Publicado: (2025)

Next-Latent Prediction Transformers Learn Compact World Models
por: Teoh, Jayden, et al.
Publicado: (2025)

Recursive Introspection: Teaching Language Model Agents How to Self-Improve
por: Qu, Yuxiao, et al.
Publicado: (2024)

Latent Action World Models for Control with Unlabeled Trajectories
por: Alles, Marvin, et al.
Publicado: (2025)

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
por: Qu, Yuxiao, et al.
Publicado: (2025)

Ethical Frameworks for Conducting Social Challenge Studies
por: Sen, Protiva, et al.
Publicado: (2025)