Publications

64 results for Parikshit Ram

Modern Methods in Associative Memory
- - Dmitry Krotov
  - Benjamin Hoover
  - et al.
- 2026
- AAAI 2026
Dense Associative Memory with Epanechnikov Energy
- - Benjamin Hoover
  - Zhaoyang Shi
  - et al.
- 2025
- NeurIPS 2025
Transformers Learn Faster with Semantic Focus
- - Parikshit Ram
  - Kenneth Clarkson
  - et al.
- 2025
- NeurIPS 2025
Specifying exact circuit algorithms in universal transformers
- - Taku Ito
  - Ruchir Puri
  - et al.
- 2025
- NeurIPS 2025
Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
- - Changsheng Wang
  - Chongyu Fan
  - et al.
- 2025
- EMNLP 2025
Quantifying artificial intelligence through algorithmic generalization
- - Takuya Ito
  - Murray Campbell
  - et al.
- 2025
- Nature Machine Intelligence
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
- - Changsheng Wang
  - Yihua Zhang
  - et al.
- 2025
- ICML 2025
Learning interpretable positional encodings in transformers depends on initialization
- - Taku Ito
  - Luca Cocchi
  - et al.
- 2025
- ICML 2025
Rethinking Unlearning for Large Reasoning Models Download PDF
- - Changsheng Wang
  - Chongyu Fan
  - et al.
- 2025
- ICML 2025
Modern Methods in Associative Memory
- - Dmitry Krotov
  - Benjamin Hoover
  - et al.
- 2025
- ICML 2025