Shantanu Dixit — accepted AI-conference papers

2026

Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity

Menglin Xia, Xuchao Zhang, Shantanu Dixit, Paramaguru Harimurugan, Rujia Wang, Victor Ruehle +3

ICML 2026poster

Agent memory systems must accommodate continuously growing information while supporting efficient, context-aware retrieval for downstream tasks. Abstraction is essential for scaling agent memory, yet it often comes at the cost of specificity, obscuring the fine-grained details required for effective…

Cited by 0 Source ↗Scholar ↗

2024

A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation

Ayan Sengupta, Shantanu Dixit, Md Shad Akhtar, Tanmoy Chakraborty

ICLR 2024poster

Knowledge distillation (KD) is a technique used to transfer knowledge from a larger ''teacher'' model into a smaller ''student'' model. Recent advancements in meta-learning-based knowledge distillation (MetaKD) emphasize that the fine-tuning of teacher models should be aware of the student's need to…

Cited by 5 Source ↗PDF ↗Scholar ↗