No official code found. Best implementation: parmanu-lcs2/mpdistil (0 stars, MIT, last commit 2025-12-15).
MPDistil is a teacher-student collaborative knowledge distillation framework that enables compact student models to outperform larger teacher models through meta-learning and curriculum learning. Based on the ICLR 2024 paper: **A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation**
An LLM can Fool Itself: A Prompt-Based Adversarial Attack
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
Consistent Adversarially Robust Linear Classification: Non-Parametric Setting
Not All Tasks Are Born Equal: Understanding Zero-Shot Generalization
Hard Tasks First: Multi-Task Reinforcement Learning Through Task Scheduling
Uni-Mol: A Universal 3D Molecular Representation Learning Framework
@article{sengupta2026good,
title = {A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation},
author = {Ayan Sengupta and Shantanu Dixit and Md. Shad Akhtar and Tanmoy Chakraborty},
year = {2026},
url = {https://api.semanticscholar.org/CorpusID:367a81167305d5e85e6a13b0dcc5434e1ed616e3},
journal = {ICLR 2024 2024}
}Shows whether official code is linked for this paper.
[](https://codeofpaper.com/paper/367a81167305d5e85e6a13b0dcc5434e1ed616e3)