Cover Image

A Complexity-Based Theory of Compositionality

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Elmoznino, Eric, Jiralerspong, Thomas, Bengio, Yoshua, Lajoie, Guillaume
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Geometric Signatures of Compositionality Across a Language Model's Lifetime
by: Lee, Jin Hwa, et al.
Published: (2024)

Discrete, compositional, and symbolic representations through attractor dynamics
by: Nam, Andrew, et al.
Published: (2023)

Amortizing intractable inference in large language models
by: Hu, Edward J., et al.
Published: (2023)

In-Context Parametric Inference: Point or Distribution Estimators?
by: Mittal, Sarthak, et al.
Published: (2025)

Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
by: Jiralerspong, Thomas, et al.
Published: (2025)

Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise
by: Scimeca, Luca, et al.
Published: (2025)

Efficient Causal Graph Discovery Using Large Language Models
by: Jiralerspong, Thomas, et al.
Published: (2024)

Next-Token Prediction Should be Ambiguity-Sensitive: A Meta-Learning Perspective
by: Gagnon, Leo, et al.
Published: (2025)

When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks
by: Lo, Chung-Hsiang, et al.
Published: (2026)

Does learning the right latent variables necessarily improve in-context learning?
by: Mittal, Sarthak, et al.
Published: (2024)

Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback
by: Jiralerspong, Thomas, et al.
Published: (2026)

A Compression Perspective on Simplicity Bias
by: Marty, Tom, et al.
Published: (2026)

In-context learning and Occam's razor
by: Elmoznino, Eric, et al.
Published: (2024)

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
by: Shojaee, Parshin, et al.
Published: (2025)

Tracing the Representation Geometry of Language Models from Pretraining to Post-training
by: Li, Melody Zixuan, et al.
Published: (2025)

Distributional GFlowNets with Quantile Flows
by: Zhang, Dinghuai, et al.
Published: (2023)

A Notion of Complexity for Theory of Mind via Discrete World Models
by: Huang, X. Angelo, et al.
Published: (2024)

When can transformers reason with abstract symbols?
by: Boix-Adsera, Enric, et al.
Published: (2023)

Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning
by: Pasewark, Eric, et al.
Published: (2024)

GFlowNet Foundations
by: Bengio, Yoshua, et al.
Published: (2021)

Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection
by: Chegini, Atoosa, et al.
Published: (2025)

Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
by: Zhang, Dinghuai, et al.
Published: (2023)

Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs
by: Jiralerspong, Thomas, et al.
Published: (2026)

MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
by: von Oswald, Johannes, et al.
Published: (2025)

CP-Prompt: Composition-Based Cross-modal Prompting for Domain-Incremental Continual Learning
by: Feng, Yu, et al.
Published: (2024)

Graph Neural Network-Based Entity Extraction and Relationship Reasoning in Complex Knowledge Graphs
by: Du, Junliang, et al.
Published: (2024)

Language Models Can Reduce Asymmetry in Information Markets
by: Rahaman, Nasim, et al.
Published: (2024)

Selective Deficits in LLM Mental Self-Modeling in a Behavior-Based Test of Theory of Mind
by: Ackerman, Christopher
Published: (2026)

Mini Minds: Exploring Bebeshka and Zlata Baby Models
by: Proskurina, Irina, et al.
Published: (2023)

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
by: Scimeca, Luca, et al.
Published: (2023)

Monte Carlo Tree Diffusion for System 2 Planning
by: Yoon, Jaesik, et al.
Published: (2025)

In-Context Reinforcement Learning through Bayesian Fusion of Context and Value Prior
by: Berkes, Anaïs, et al.
Published: (2026)

A Critical Evaluation of AI Feedback for Aligning Large Language Models
by: Sharma, Archit, et al.
Published: (2024)

ComplexityNet: Increasing LLM Inference Efficiency by Learning Task Complexity
by: Bae, Henry, et al.
Published: (2023)

Beyond Distribution Sharpening: The Importance of Task Rewards
by: Mittal, Sarthak, et al.
Published: (2026)

Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding
by: Ryu, Hyun, et al.
Published: (2024)

Dynamic Universal Approximation Theory: The Basic Theory for Transformer-based Large Language Models
by: Wang, Wei, et al.
Published: (2024)

Exposing propaganda: an analysis of stylistic cues comparing human annotations and machine classification
by: Faye, Géraud, et al.
Published: (2024)

Instruct-Tuning Pretrained Causal Language Models for Ancient Greek Papyrology and Epigraphy
by: Cullhed, Eric
Published: (2024)

MemEIC: A Step Toward Continual and Compositional Knowledge Editing
by: Seong, Jin, et al.
Published: (2025)