Publications of Hemanth Saratchandran sorted by title
C
| Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks, , , and , in: International Conference on Learning Representations, 2026 |
[URL] |
| Can you learn to see without images? procedural warm-up for vision transformers, , , , and , in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026 |
[URL] |
L
| Language Models Can Benefit from Domain-Specific Inductive Biases, , , , and , in: Conference on Neural Information Processing Systems, 2026 |
|
P
| Procedural pretraining: Warming up language models with abstract data, , , , and , in: International Conference on Machine Learning, 2026 |
[URL] |
T
| Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning, , , , and , in: ICML 2025 Workshop on Methods and Opportunities at Small Scale, 2025 |
|