Imagen de Portada

Relational reasoning and inductive bias in transformers and large language models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Geerts, Jesse, Liu, Andrew, Chan, Stephanie, Clopath, Claudia, Stachenfeld, Kimberly
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Neurons and Cognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Cortico-cerebellar modularity as an architectural inductive bias for efficient temporal learning
por: Voce, Alexandra, et al.
Publicado: (2026)

When does compositional structure yield compositional generalization? A kernel theory
por: Lippl, Samuel, et al.
Publicado: (2024)

Representation biases: will we achieve complete understanding by analyzing representations?
por: Lampinen, Andrew Kyle, et al.
Publicado: (2025)

Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay
por: Oota, Subba Reddy, et al.
Publicado: (2026)

A foundation model of vision, audition, and language for in-silico neuroscience
por: d'Ascoli, Stéphane, et al.
Publicado: (2026)

Integrative neurocybernetic modeling in the era of large-scale neuroscience
por: Park, Il Memming, et al.
Publicado: (2026)

A Concise Mathematical Description of Active Inference in Discrete Time
por: van Oostrum, Jesse, et al.
Publicado: (2024)

Brain-language fusion enables interactive neural readout and in-silico experimentation
por: Bosch, Victoria, et al.
Publicado: (2025)

Representations in vision and language converge in a shared, multidimensional space of perceived similarities
por: Simkova, Katerina Marie, et al.
Publicado: (2025)

Visual representations in the human brain are aligned with large language models
por: Doerig, Adrien, et al.
Publicado: (2022)

Embodiment in multimodal large language models
por: Kadambi, Akila, et al.
Publicado: (2025)

Adversarial construction as a potential solution to the experiment design problem in large task spaces
por: Godara, Prakhar, et al.
Publicado: (2026)

Unsupervised discovery of the shared and private geometry in multi-view data
por: Koukuntla, Sai, et al.
Publicado: (2024)

Analyzing heterogeneity in Alzheimer Disease using multimodal normative modeling on imaging-based ATN biomarkers
por: Kumar, Sayantan, et al.
Publicado: (2024)

Nonlinear Dynamical Modeling of Human Intracranial Brain Activity with Flexible Inference
por: Vaziri, Kiarash, et al.
Publicado: (2025)

Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)
por: Oota, Subba Reddy, et al.
Publicado: (2025)

Large language models reorganize representational geometry during in-context learning
por: Xiong, Hua-Dong, et al.
Publicado: (2026)

Algorithm Development in Neural Networks: Insights from the Streaming Parity Task
por: van Rossem, Loek, et al.
Publicado: (2025)

When Representations Align: Universality in Representation Learning Dynamics
por: van Rossem, Loek, et al.
Publicado: (2024)

Deep probabilistic model synthesis enables unified modeling of whole-brain neural activity across individual subjects
por: Bishop, William E., et al.
Publicado: (2026)

Charting trajectories of human thought using large language models
por: Nour, Matthew M, et al.
Publicado: (2025)

The Gaussian-Linear Hidden Markov model: a Python package
por: Vidaurre, Diego, et al.
Publicado: (2023)

A ghost mechanism: An analytical model of abrupt learning in recurrent networks
por: Dinc, Fatih, et al.
Publicado: (2025)

Generalizable, real-time neural decoding with hybrid state-space models
por: Ryoo, Avery Hee-Woon, et al.
Publicado: (2025)

Decomposing stimulus-specific sensory neural information via diffusion models
por: Laquitaine, Steeve, et al.
Publicado: (2025)

BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity
por: Luo, Andrew F., et al.
Publicado: (2023)

Unsupervised learning of multiscale switching dynamical system models from multimodal neural data
por: Kim, DongKyu, et al.
Publicado: (2025)

Construction of a classification model for dementia among Brazilian adults aged 50 and over
por: Menezes, F. S., et al.
Publicado: (2026)

HDGL: A hierarchical dynamic graph representation learning model for brain disorder classification
por: Jalali, Parnian, et al.
Publicado: (2023)

Flexible task abstractions emerge in linear networks with fast and bounded units
por: Sandbrink, Kai, et al.
Publicado: (2024)

A flexible Bayesian non-parametric mixture model reveals multiple dependencies of swap errors in visual working memory
por: Radmard, Puria, et al.
Publicado: (2025)

Deep learning and whole-brain networks for biomarker discovery: modeling the dynamics of brain fluctuations in resting-state and cognitive tasks
por: Roffet, Facundo, et al.
Publicado: (2024)

Diffusion-Based Generation of Neural Activity from Disentangled Latent Codes
por: McCart, Jonathan D., et al.
Publicado: (2024)

Active learning of neural population dynamics using two-photon holographic optogenetics
por: Wagenmaker, Andrew, et al.
Publicado: (2024)

Active inference and artificial reasoning
por: Friston, Karl, et al.
Publicado: (2025)

Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex
por: Yu, Muquan, et al.
Publicado: (2025)

DCHO: A Decomposition-Composition Framework for Predicting Higher-Order Brain Connectivity to Enhance Diverse Downstream Applications
por: Li, Weibin, et al.
Publicado: (2025)

Does Feedback Alignment Work at Biological Timescales?
por: Bacvanski, Marc Gong, et al.
Publicado: (2025)

Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding
por: Nan, Mu, et al.
Publicado: (2026)

HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses
por: Deng, Zhichao, et al.
Publicado: (2025)