Image de couverture de livre

Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dupoux, Emmanuel, LeCun, Yann, Malik, Jitendra
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Fast and Exact Enumeration of Deep Networks Partitions Regions
par: Balestriero, Randall, et autres
Publié: (2024)

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
par: Balestriero, Randall, et autres
Publié: (2025)

Learning by Reconstruction Produces Uninformative Features For Perception
par: Balestriero, Randall, et autres
Publié: (2024)

Intuitive physics understanding emerges from self-supervised pretraining on natural videos
par: Garrido, Quentin, et autres
Publié: (2025)

Whole-Body Conditioned Egocentric Video Prediction
par: Bai, Yutong, et autres
Publié: (2025)

AI Must Embrace Specialization via Superhuman Adaptable Intelligence
par: Goldfeder, Judah, et autres
Publié: (2026)

LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
par: Huang, Hai, et autres
Publié: (2025)

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
par: Zhou, Gaoyue, et autres
Publié: (2024)

Video Representation Learning with Joint-Embedding Predictive Architectures
par: Drozdov, Katrina, et autres
Publié: (2024)

The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
par: Sun, Shangwen, et autres
Publié: (2026)

Causal-JEPA: Learning World Models through Object-Level Latent Masking
par: Nam, Heejeong, et autres
Publié: (2026)

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
par: Maes, Lucas, et autres
Publié: (2026)

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
par: Balestriero, Randall, et autres
Publié: (2025)

Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning
par: Moutakanni, Théo, et autres
Publié: (2024)

Value-guided action planning with JEPA world models
par: Destrade, Matthieu, et autres
Publié: (2025)

Blockwise Self-Supervised Learning at Scale
par: Siddiqui, Shoaib Ahmed, et autres
Publié: (2023)

Light-weight probing of unsupervised representations for Reinforcement Learning
par: Zhang, Wancong, et autres
Publié: (2022)

What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
par: Terver, Basile, et autres
Publié: (2025)

stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation
par: Maes, Lucas, et autres
Publié: (2026)

From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
par: Shani, Chen, et autres
Publié: (2025)

Navigation World Models
par: Bar, Amir, et autres
Publié: (2024)

Transformers without Normalization
par: Zhu, Jiachen, et autres
Publié: (2025)

An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization
par: Shwartz-Ziv, Ravid, et autres
Publié: (2023)

Variance-Covariance Regularization Improves Representation Learning
par: Zhu, Jiachen, et autres
Publié: (2023)

Learning Latent Action World Models In The Wild
par: Garrido, Quentin, et autres
Publié: (2026)

Learning what they think vs. learning what they do: The micro-foundations of vicarious learning
par: Park, Sanghyun, et autres
Publié: (2020)

Shh, don't say that! Domain Certification in LLMs
par: Emde, Cornelius, et autres
Publié: (2025)

Learning and Leveraging World Models in Visual Representation Learning
par: Garrido, Quentin, et autres
Publié: (2024)

Ask don't tell: Reducing sycophancy in large language models
par: Dubois, Magda, et autres
Publié: (2026)

On the consistent reasoning paradox of intelligence and optimal trust in AI: The power of 'I don't know'
par: Bastounis, Alexander, et autres
Publié: (2024)

Lessons from Learning to Spin "Pens"
par: Wang, Jun, et autres
Publié: (2024)

“I know what I don't know”: Metacognition in leadership learning
par: Jillian Volpe‐White
Publié: (2024)

Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
par: Rudman, William, et autres
Publié: (2025)

Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
par: Queipo-de-Llano, Enrique, et autres
Publié: (2025)

Hierarchical learning control for autonomous robots inspired by central nervous system
par: Zhang, Pei, et autres
Publié: (2024)

Revisiting Feature Prediction for Learning Visual Representations from Video
par: Bardes, Adrien, et autres
Publié: (2024)

Layer by Layer: Uncovering Hidden Representations in Language Models
par: Skean, Oscar, et autres
Publié: (2025)

SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation
par: Luthra, Mahi, et autres
Publié: (2025)

JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention
par: Ioannides, Georgios, et autres
Publié: (2025)

Introduction to Latent Variable Energy-Based Models: A Path Towards Autonomous Machine Intelligence
par: Dawid, Anna, et autres
Publié: (2023)