Cover Image

From monoliths to modules: Decomposing transducers for efficient world modelling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Boyd, Alexander, Nowak, Franz, Hyland, David, Baltieri, Manuel, Rosas, Fernando E.
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability
by: Rosas, Fernando, et al.
Published: (2025)

Disentangled Representations for Causal Cognition
by: Torresan, Filippo, et al.
Published: (2024)

Prior preferences in active inference agents: soft, hard, and goal shaping
by: Torresan, Filippo, et al.
Published: (2025)

A "good regulator theorem" for embodied agents
by: Virgo, Nathaniel, et al.
Published: (2025)

Active inference for action-unaware agents
by: Torresan, Filippo, et al.
Published: (2025)

On the Variational Costs of Changing Our Minds
by: Hyland, David, et al.
Published: (2025)

Efficient Parallel Algorithm for Decomposing Hard CircuitSAT Instances
by: Kondratiev, Victor, et al.
Published: (2026)

A Primer on Large Language Models and their Limitations
by: Johnson, Sandra, et al.
Published: (2024)

Effective internal language model training and fusion for factorized transducer model
by: Guo, Jinxi, et al.
Published: (2024)

Advancing site-specific disease and pest management in precision agriculture: From reasoning-driven foundation models to adaptive, feedback-based learning
by: Rai, Nitin, et al.
Published: (2025)

Inducing Personality in LLM-Based Honeypot Agents: Measuring the Effect on Human-Like Agenda Generation
by: Newsham, Lewis, et al.
Published: (2025)

Can GPT-4 learn to analyse moves in research article abstracts?
by: Yu, Danni, et al.
Published: (2024)

Estimating the Self-Consistency of LLMs
by: Nowak, Robert
Published: (2025)

An Autonomous Non-monolithic Agent with Multi-mode Exploration based on Options Framework
by: Kim, JaeYoon, et al.
Published: (2023)

SENS-ASR: Semantic Embedding injection in Neural-transducer for Streaming Automatic Speech Recognition
by: Dkhissi, Youness, et al.
Published: (2026)

From task structures to world models: What do LLMs know?
by: Yildirim, Ilker, et al.
Published: (2023)

Synthesizing world models for bilevel planning
by: Ahmed, Zergham, et al.
Published: (2025)

Assessing model error in counterfactual worlds
by: Howerton, Emily, et al.
Published: (2025)

General agents contain world models
by: Richens, Jonathan, et al.
Published: (2025)

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning
by: Robertson, Cole, et al.
Published: (2025)

PairVDN - Pair-wise Decomposed Value Functions
by: Buzzard, Zak
Published: (2025)

Algebras of actions in an agent's representations of the world
by: Dean, Alexander, et al.
Published: (2023)

Bringing together invertible UNets with invertible attention modules for memory-efficient diffusion models
by: Jain, Karan, et al.
Published: (2025)

QUINTA: Reflexive Sensibility For Responsible AI Research and Data-Driven Processes
by: Boyd, Alicia E.
Published: (2025)

Decompose the model: Mechanistic interpretability in image models with Generalized Integrated Gradients (GIG)
by: Kim, Yearim, et al.
Published: (2024)

Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models
by: Westphal, Charles, et al.
Published: (2026)

Neurons for Neutrons: A Transformer Model for Computation Load Estimation on Domain-Decomposed Neutron Transport Problems
by: Mote, Alexander, et al.
Published: (2024)

Towards More Efficient Shared Autonomous Mobility: A Learning-Based Fleet Repositioning Approach
by: Filipovska, Monika, et al.
Published: (2022)

Decomposability-Guaranteed Cooperative Coevolution for Large-Scale Itinerary Planning
by: Zhang, Ziyu, et al.
Published: (2025)

The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features
by: Ferrao, Jeremias, et al.
Published: (2025)

Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation
by: Zheng, Lulu, et al.
Published: (2026)

Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing
by: Wang, Miao, et al.
Published: (2026)

Truck Parking Usage Prediction with Decomposed Graph Neural Networks
by: Tamaru, Rei, et al.
Published: (2024)

Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner
by: Eschenhagen, Runa, et al.
Published: (2025)

Closed-form merging of parameter-efficient modules for Federated Continual Learning
by: Salami, Riccardo, et al.
Published: (2024)

Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models
by: Liu, Shuodi, et al.
Published: (2025)

A Parallel Approach to Counting Exact Covers Based on Decomposability Property
by: Fang, Liangda, et al.
Published: (2026)

StructRL: Recovering Dynamic Programming Structure from Learning Dynamics in Distributional Reinforcement Learning
by: Nowak, Ivo
Published: (2026)

Decomposing Epistemic Uncertainty for Causal Decision Making
by: Rahman, Md Musfiqur, et al.
Published: (2026)

SDQ: Sparse Decomposed Quantization for LLM Inference
by: Jeong, Geonhwa, et al.
Published: (2024)