Please note that ISTA Research Explorer no longer supports Internet Explorer versions 8 or 9 (or earlier).
We recommend upgrading to the latest Internet Explorer, Google Chrome, or Firefox.
7 Publications
2025 | Published | Conference Paper | IST-REx-ID: 20038 | 
Jin, Tian, et al. “The Journey Matters: Average Parameter Count over Pre-Training Unifies Sparse and Dense Scaling Laws.” 13th International Conference on Learning Representations, ICLR, 2025, pp. 85165–81.
[Published Version]
View
| Files available
| arXiv
2025 | Published | Conference Paper | IST-REx-ID: 20033 |
Emrullah Ildiz, M., et al. “High-Dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws.” 13th International Conference on Learning Representations, ICLR, 2025, pp. 2967–3006.
[Published Version]
View
| Files available
| arXiv
2025 | Published | Conference Paper | IST-REx-ID: 20037 |
Sawmya, Shashata, et al. “Wasserstein Distances, Neuronal Entanglement, and Sparsity.” 13th International Conference on Learning Representations, ICLR, 2025, pp. 26244–74.
[Published Version]
View
| Files available
| arXiv
2025 | Published | Conference Paper | IST-REx-ID: 20036 |
Pariza, Valentinos, et al. “Near, Far: Patch-Ordering Enhances Vision Foundation Models’ Scene Understanding.” 13th International Conference on Learning Representations, ICLR, 2025, pp. 72303–30.
[Published Version]
View
| Files available
| arXiv
2025 | Published | Conference Paper | IST-REx-ID: 20032 |
Chen, Jiale, et al. “Scalable Mechanistic Neural Networks.” 13th International Conference on Learning Representations, ICLR, 2025, pp. 63716–37.
[Published Version]
View
| Files available
| arXiv
2025 | Published | Conference Paper | IST-REx-ID: 20035 |
Jacot, Arthur, et al. “Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse.” 13th International Conference on Learning Representations, ICLR, 2025, pp. 1905–31.
[Published Version]
View
| Files available
| arXiv
2025 | Published | Conference Paper | IST-REx-ID: 20034 |
Robert, Thomas, et al. “LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics.” 13th International Conference on Learning Representations, ICLR, 2025, pp. 101877–913.
[Published Version]
View
| Files available
| arXiv