Md. Rifat Arefin, Gopeshh Subbaraj, Nicolas Gontier, Yann LeCun, Irina Rish, Ravid Shwartz-Ziv and Christopher J. Pal
Paper (2025)
 Open Acess document at official publisher |
| Additional Information: | Scripts : https://github.com/rarefin/SEQ_VCR/blob/main/README.md |
|---|---|
| Department: | Department of Computer Engineering and Software Engineering |
| PolyPublie URL: | https://publications.polymtl.ca/66812/ |
| Conference Title: | 13th International Conference on Learning Representations (ICLR 2025) |
| Conference Location: | Singapore, Singapore |
| Conference Date(s): | 2025-04-24 - 2025-04-28 |
| Official URL: | https://proceedings.iclr.cc/paper_files/paper/2025... |
| Date Deposited: | 28 Jul 2025 15:22 |
| Last Modified: | 28 Jul 2025 15:35 |
| Cite in APA 7: | Rifat Arefin, M., Subbaraj, G., Gontier, N., LeCun, Y., Rish, I., Shwartz-Ziv, R., & Pal, C. J. (2025, April). SEQ-VCR : preventing collapse in intermediate transformer representations for enhanced reasoning [Paper]. 13th International Conference on Learning Representations (ICLR 2025), Singapore, Singapore. https://proceedings.iclr.cc/paper_files/paper/2025/hash/b577c062bd4f894b7e05fab6440373ed-Abstract-Conference.html |
|---|---|
Statistics
Stats are not available on this system.
Repository Staff Only
|
View Item |
