Image de couverture de livre

Dissociating model architectures from inference computations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sajid, Noor, Medrano, Johan
Format:	Preprint
Publié:	2025
Sujets:	Neurons and Cognition Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A broken duet: multistable dynamics of dyadic interactions
par: Medrano, Johan, et autres
Publié: (2024)

On efficient computation in active inference
par: Paul, Aswin, et autres
Publié: (2023)

Large language models reorganize representational geometry during in-context learning
par: Xiong, Hua-Dong, et autres
Publié: (2026)

A Spatio-Temporal Point Process for Fine-Grained Modeling of Reading Behavior
par: Re, Francesco Ignazio, et autres
Publié: (2025)

Optimizing fMRI Data Acquisition for Decoding Natural Speech with Limited Participants
par: Jalouzot, Louis, et autres
Publié: (2025)

Characterizing Human Semantic Navigation in Concept Production as Trajectories in Embedding Space
par: Toro-Hernández, Felipe D., et autres
Publié: (2026)

MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding
par: Chen, Zexuan, et autres
Publié: (2026)

What Are We Actually Decoding? Source Attribution for Non-Invasive Brain-to-Language Retrieval
par: Zhang, Xinyu, et autres
Publié: (2026)

Brain-to-Text Benchmark '24: Lessons Learned
par: Willett, Francis R., et autres
Publié: (2024)

Three tiers of computation in transformers and in brain architectures
par: Graham, E, et autres
Publié: (2025)

Linguistic properties and model scale in brain encoding: from small to compressed language models
par: Oota, Subba Reddy, et autres
Publié: (2026)

Integrating large language models and active inference to understand eye movements in reading and dyslexia
par: Donnarumma, Francesco, et autres
Publié: (2023)

Large language models are not about natural language
par: Bolhuis, Johan J., et autres
Publié: (2025)

Neural timescales from a computational perspective
par: Zeraati, Roxana, et autres
Publié: (2024)

Compositional meta-learning through probabilistic task inference
par: Bakermans, Jacob J. W., et autres
Publié: (2025)

Scalable inference of functional neural connectivity at submillisecond timescales
par: Medvedeva, Arina, et autres
Publié: (2025)

EmoMind: Decoding Affective Captions from Human Brain fMRI
par: Mohammed, Bilal A., et autres
Publié: (2026)

Triple Phase Transitions: Understanding the Learning Dynamics of Large Language Models from a Neuroscience Perspective
par: Nakagi, Yuko, et autres
Publié: (2025)

Sparks of cognitive flexibility: self-guided context inference for flexible stimulus-response mapping by attentional routing
par: Sommers, Rowan P., et autres
Publié: (2025)

Speech language models lack important brain-relevant semantics
par: Oota, Subba Reddy, et autres
Publié: (2023)

Riemannian Geometry for the classification of brain states with intracortical brain-computer interfaces
par: Marin-Llobet, Arnau, et autres
Publié: (2025)

Separating the what and how of compositional computation to enable reuse and continual learning
par: Shan, Haozhe, et autres
Publié: (2025)

BSD: a Bayesian framework for parametric models of neural spectra
par: Medrano, Johan, et autres
Publié: (2024)

Scaling and context steer LLMs along the same computational path as the human brain
par: Raugel, Joséphine, et autres
Publié: (2025)

In Praise of Stubbornness: An Empirical Case for Cognitive-Dissonance Aware Continual Update of Knowledge in LLMs
par: Clemente, Simone, et autres
Publié: (2025)

sEEG-based Encoding for Sentence Retrieval: A Contrastive Learning Approach to Brain-Language Alignment
par: Liu, Yijun
Publié: (2025)

Self-Organizing Language
par: Eugenio, P. Myles, et autres
Publié: (2025)

NeuroNarrator: A Generalist EEG-to-Text Foundation Model for Clinical Interpretation via Spectro-Spatial Grounding and Temporal State-Space Reasoning
par: Wang, Guoan, et autres
Publié: (2026)

Crafting Interpretable Embeddings by Asking LLMs Questions
par: Benara, Vinamra, et autres
Publié: (2024)

On the Shape of Brainscores for Large Language Models (LLMs)
par: Li, Jingkai
Publié: (2024)

Divergences between Language Models and Human Brains
par: Zhou, Yuchen, et autres
Publié: (2023)

Human-inspired Episodic Memory for Infinite Context LLMs
par: Fountas, Zafeirios, et autres
Publié: (2024)

Not All Errors Are Equal: Investigation of Speech Recognition Errors in Alzheimer's Disease Detection
par: Kang, Jiawen, et autres
Publié: (2024)

Can Brain Signals Reveal Inner Alignment with Human Languages?
par: Han, William, et autres
Publié: (2022)

Aspects of human memory and Large Language Models
par: Janik, Romuald A.
Publié: (2023)

Emergence of psychopathological computations in large language models
par: Lee, Soo Yong, et autres
Publié: (2025)

Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment
par: Wu, Hanlin, et autres
Publié: (2025)

Estimating Brain Activity with High Spatial and Temporal Resolution using a Naturalistic MEG-fMRI Encoding Model
par: Jin, Beige Jerry, et autres
Publié: (2025)

Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference
par: Erturk, Eray, et autres
Publié: (2025)

Meta predictive learning model of languages in neural circuits
par: Li, Chan, et autres
Publié: (2023)