Imagen de Portada

World Model Robustness via Surprise Recognition

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zollicoffer, Geigh, Chopra, Tanush, Yan, Mingkuan, Ma, Xiaoxu, Eaton, Kenneth, Riedl, Mark
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Novelty Detection in Reinforcement Learning with World Models
por: Zollicoffer, Geigh, et al.
Publicado: (2023)

Is Exploration All You Need? Effective Exploration Characteristics for Transfer in Reinforcement Learning
por: Balloch, Jonathan C., et al.
Publicado: (2024)

The Interpretability of Codebooks in Model-Based Reinforcement Learning is Limited
por: Eaton, Kenneth, et al.
Publicado: (2024)

HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling
por: Vu, Minh, et al.
Publicado: (2025)

View From Above: A Framework for Evaluating Distribution Shifts in Model Behavior
por: Chopra, Tanush, et al.
Publicado: (2024)

Topological Signatures of Adversaries in Multimodal Alignments
por: Vu, Minh, et al.
Publicado: (2025)

LoRID: Low-Rank Iterative Diffusion for Adversarial Purification
por: Zollicoffer, Geigh, et al.
Publicado: (2024)

LaFA: Latent Feature Attacks on Non-negative Matrix Factorization
por: Vu, Minh, et al.
Publicado: (2024)

MTRE: Multi-Token Reliability Estimation for Hallucination Detection in VLMs
por: Zollicoffer, Geigh, et al.
Publicado: (2025)

Accelerating Matrix Diagonalization through Decision Transformers with Epsilon-Greedy Optimization
por: Bhatta, Kshitij, et al.
Publicado: (2024)

Towards Faster Matrix Diagonalization with Graph Isomorphism Networks and the AlphaZero Framework
por: Zollicoffer, Geigh, et al.
Publicado: (2024)

Hybrid Neural World Models
por: Lakshmanan, Pranav, et al.
Publicado: (2026)

Surprisal Driven $k$-NN for Robust and Interpretable Nonparametric Learning
por: Banerjee, Amartya, et al.
Publicado: (2023)

The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling
por: Ma, Jiajun, et al.
Publicado: (2024)

External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling
por: Bhagat, Rishav, et al.
Publicado: (2024)

Verification of the Implicit World Model in a Generative Model via Adversarial Sequences
por: Balogh, András, et al.
Publicado: (2026)

EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages
por: Sharma, Aman, et al.
Publicado: (2026)

Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs
por: Ma, Xin, et al.
Publicado: (2024)

Sanity Checks for Long-Form Hallucination Detection
por: Zollicoffer, Geigh, et al.
Publicado: (2026)

On the Surprising Efficacy of Distillation as an Alternative to Pre-Training Small Models
por: Farhat, Sean, et al.
Publicado: (2024)

Mosaic Pruning: A Hierarchical Framework for Generalizable Pruning of Mixture-of-Experts Models
por: Hu, Wentao, et al.
Publicado: (2025)

History Rhymes: Macro-Contextual Retrieval for Robust Financial Forecasting
por: Khanna, Sarthak, et al.
Publicado: (2025)

Model Agreement via Anchoring
por: Eaton, Eric, et al.
Publicado: (2026)

On Surprising Effectiveness of Masking Updates in Adaptive Optimizers
por: Joo, Taejong, et al.
Publicado: (2026)

Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities
por: Chandhok, Shivam, et al.
Publicado: (2025)

Influence functions and regularity tangents for efficient active learning
por: Eaton, Frederik
Publicado: (2024)

The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute
por: Sharma, Aman, et al.
Publicado: (2025)

Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
por: Sharma, Aman, et al.
Publicado: (2025)

Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts
por: Trehan, Dhruv, et al.
Publicado: (2026)

Discovering Reinforcement Learning Interfaces with Large Language Models
por: Jaswal, Akshat Singh, et al.
Publicado: (2026)

Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning
por: Hugessen, Adriana, et al.
Publicado: (2024)

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction
por: GX-Chen, Anthony, et al.
Publicado: (2024)

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

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
por: Liu, Huihan, et al.
Publicado: (2026)

AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise
por: Agarwal, Dhruv, et al.
Publicado: (2025)

On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
por: Haas, Moritz, et al.
Publicado: (2025)

Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection
por: Özer, Kadir-Kaan, et al.
Publicado: (2026)

Discrete World Models via Regularization
por: Bizzaro, Davide, et al.
Publicado: (2026)

Building Interpretable Models for Moral Decision-Making
por: Goel, Mayank, et al.
Publicado: (2026)

Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
por: Cheng, Jie, et al.
Publicado: (2024)