---

1. Self-supervised DXA representations encode multi-system disease risk, biological aging and heritability
   2026-08-03alphaXiv arXiv S2
2. HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning
   2026-08-01alphaXiv arXiv S2
3. Unpacking Open Source Artificial Intelligence: Toward a Framework for Openness in Foundation Models
   Communications of the ACM2026-07-29S2
4. Music-JEPA: Learning a World Model of Sound from Action
   2026-07-24alphaXiv arXiv S2
5. Patch Policy: Efficient Embodied Control via Dense Visual Representations
   2026-07-20alphaXiv arXiv S2
6. Separating Representation from Reconstruction Enables Scalable Text Encoders
   2026-07-04alphaXiv arXiv S2
7. AdaJEPA: An Adaptive Latent World Model
   arXiv.org2026-06-30alphaXiv arXiv S2
8. SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors
   arXiv.org2026-06-22alphaXiv arXiv S2
9. S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning
   arXiv.org2026-06-17alphaXiv arXiv S2
10. You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences
    arXiv.org2026-06-14alphaXiv arXiv S2
11. Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks
    arXiv.org2026-06-07alphaXiv arXiv S2
12. When Does LeJEPA Learn a World Model?
    arXiv.org2026-05-25alphaXiv arXiv S2
13. Announcing the Shaw Prize in Computer Science
    Communications of the ACM2026-05-21S2
14. stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
    arXiv.org2026-05-20alphaXiv arXiv S2
15. Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement
    arXiv.org2026-05-14alphaXiv arXiv S2
16. On Training in Imagination
    arXiv.org2026-05-07alphaXiv arXiv S2
17. Spectral Graph Theory: The mathematics of self-supervised learning [Special Issue on the Mathematics of Deep Learning]
    IEEE Signal Processing Magazine2026-05-01S2
18. Hierarchical Planning with Latent World Models
    arXiv.org2026-04-03alphaXiv arXiv S2
19. Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science
    arXiv.org2026-03-16alphaXiv arXiv S2
20. V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
    arXiv.org2026-03-15alphaXiv arXiv S2
21. Representation Learning for Spatiotemporal Physical Systems
    arXiv.org2026-03-13alphaXiv arXiv S2
22. LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
    arXiv.org2026-03-13alphaXiv arXiv S2
23. Temporal Straightening for Latent Planning
    arXiv.org2026-03-12alphaXiv arXiv S2
24. The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
    arXiv.org2026-03-05alphaXiv arXiv S2
25. AI+HW 2035: Shaping the Next Decade
    arXiv.org2026-03-05alphaXiv arXiv S2
26. Beyond Language Modeling: An Exploration of Multimodal Pretraining
    arXiv.org2026-03-03alphaXiv arXiv S2
27. AI Must Embrace Specialization via Superhuman Adaptable Intelligence
    arXiv.org2026-02-27alphaXiv arXiv S2
28. Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA
    arXiv.org2026-02-26alphaXiv arXiv S2
29. Radial-VCReg: More Informative Representation Learning Through Radial Gaussianization
    arXiv.org2026-02-15alphaXiv arXiv S2
30. Causal-JEPA: Learning World Models through Object-Level Latent Masking
    2026-02-11alphaXiv arXiv S2
31. stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation
    arXiv.org2026-02-09alphaXiv arXiv S2
32. A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures
    arXiv.org2026-02-03alphaXiv arXiv S2
33. Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
    arXiv.org2026-02-01alphaXiv arXiv S2
34. Parallel Stochastic Gradient-Based Planning for World Models
    arXiv.org2026-01-31alphaXiv arXiv S2
35. Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures
    arXiv.org2026-01-30alphaXiv arXiv S2
36. Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
    arXiv.org2026-01-22alphaXiv arXiv S2
37. Learning Latent Action World Models In The Wild
    arXiv.org2026-01-08alphaXiv arXiv S2
38. Causal-JEPA: Learning World Models through Object-Level Latent Interventions
    arXiv.org2026S2
39. What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
    Trans. Mach. Learn. Res.2025-12-30alphaXiv arXiv S2
40. Value-guided action planning with JEPA world models
    arXiv.org2025-12-28alphaXiv arXiv S2
41. SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation
    Annual Meeting of the Association for Computational Linguistics2025-12-24alphaXiv arXiv S2
42. Closing the Train-Test Gap in World Models for Gradient-Based Planning
    arXiv.org2025-12-10alphaXiv arXiv S2
43. JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention
    arXiv.org2025-12-08alphaXiv arXiv S2
44. LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
    arXiv.org2025-11-11alphaXiv arXiv S2
45. Cambrian-S: Towards Spatial Supersensing in Video
    arXiv.org2025-11-06alphaXiv arXiv S2
46. Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
    arXiv.org2025-10-07alphaXiv arXiv S2
47. Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
    arXiv.org2025-10-07alphaXiv arXiv S2
48. LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
    arXiv.org2025-09-11alphaXiv arXiv S2
49. Back to the Features: DINO as a Foundation for Video World Models
    arXiv.org2025-07-25alphaXiv arXiv S2
50. V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
    arXiv.org2025-06-11alphaXiv arXiv S2
51. OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation
    Neural Information Processing Systems2025-05-26alphaXiv arXiv S2
52. From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
    arXiv.org2025-05-21alphaXiv arXiv S2
53. Scaling Language-Free Visual Representation Learning
    IEEE International Conference on Computer Vision2025-04-01alphaXiv arXiv S2
54. Transformers without Normalization
    Computer Vision and Pattern Recognition2025-03-13alphaXiv arXiv S2
55. Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models
    Neural Information Processing Systems2025-02-20alphaXiv arXiv S2
56. Intuitive physics understanding emerges from self-supervised pretraining on natural videos
    arXiv.org2025-02-17alphaXiv arXiv S2
57. Layer by Layer: Uncovering Hidden Representations in Language Models
    International Conference on Machine Learning2025-02-04alphaXiv arXiv S2
58. Artificial Intelligence in Scientific Research: Transforming Data Analysis and Discovery
    International Journal of Innovative Computer Science and IT Research2025-01-01S2
59. Training compute-optimal transformer encoder models
    Conference on Empirical Methods in Natural Language Processing2025S2
60. MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
    IEEE International Conference on Computer Vision2024-12-18alphaXiv arXiv S2
61. Video Representation Learning with Joint-Embedding Predictive Architectures
    arXiv.org2024-12-14alphaXiv arXiv S2
62. Does Representation Matter? Exploring Intermediate Layers in Large Language Models
    arXiv.org2024-12-12alphaXiv arXiv S2
63. Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation
    Computer Vision and Pattern Recognition2024-12-10alphaXiv arXiv S2
64. Navigation World Models
    Computer Vision and Pattern Recognition2024-12-04alphaXiv arXiv S2
65. Improving Pre-Trained Self-Supervised Embeddings Through Effective Entropy Maximization
    International Conference on Artificial Intelligence and Statistics2024-11-24alphaXiv arXiv S2
66. FAST INCREMENTAL LEARNING FOR AUTONOMOUS GROUND NAVIGATION
    SAE technical paper series2024-11-15S2
67. DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
    International Conference on Machine Learning2024-11-07alphaXiv arXiv S2
68. Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
    International Conference on Learning Representations2024-11-04alphaXiv arXiv S2
69. Multi-modal AI for comprehensive breast cancer prognostication
    Nature Communications2024-10-28alphaXiv arXiv S2
70. PooDLe: Pooled and dense self-supervised learning from naturalistic videos
    International Conference on Learning Representations2024-08-20alphaXiv arXiv S2
71. LiveBench: A Challenging, Contamination-Free LLM Benchmark
    arXiv.org2024S2
72. 𝕏-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
    arXiv.org2024S2
73. How Learning by Reconstruction Produces Uninformative Features For Perception
    International Conference on Machine Learning2024S2
74. Minimalistic Unsupervised Representation Learning with the Sparse Manifold Transform
    International Conference on Learning Representations2023S2
75. An Information Theory Perspective on Variance-Invariance-Covariance Regularization
    Neural Information Processing Systems2023S2
76. An Information Theory Perspective on Variance-Invariance-Covariance Regularization
    Advances in Neural Information Processing Systems 362023S2
77. International Conference on Machine Learning June 2014, Bejing China Workshop Ulearbnbio Unsupervised Learning for Bioacoustic Data High Performance Computer Acoustic Data Accelerator: a New System for Exploring Marine Mammal Acoustics for Big Data Applications
    S2
78. Energy-based Models in Document Recognition and Computer Vision. 1. Two Challenges in Machine Learning
    S2
79. The Diashow Paradox: Stronger 3D-Aware Representations Emerge from Image Sets, Not Videos Anonymous ICCV submission
    S2
80. An Information-Theoretic Understanding of Maximum Manifold Capacity Representations
    S2