Related papers: Developing signal processing skills: A proposal fo…
There is increasing interest in distilling task-specific knowledge from large language models (LLM) to smaller student models. Nonetheless, LLM distillation presents a dual challenge: 1) there is a high cost associated with querying the…
A close look at students' written work on examinations offers a wealth of information about their performance, their knowledge of the subject, their strengths, weaknesses and misconceptions, and their overall level of mathematical skills…
Accurate estimation of the states of a nonlinear dynamical system is crucial for their design, synthesis, and analysis. Particle filters are estimators constructed by simulating trajectories from a sampling distribution and averaging them…
Intelligent Tutoring Systems often grant learners shared control over skill and problem selection. This choice brings motivational and metacognitive benefits. At the same time, past literature suggests that learners exhibit diverse…
A learning algorithm based on primary school teaching and learning is presented. The methodology is to continuously evaluate a student and to give them training on the examples for which they repeatedly fail, until, they can correctly…
Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on random data shuffling, without any…
When executed well, project-based learning (PBL) engages students' intrinsic motivation, encourages students to learn far beyond a course's limited curriculum, and prepares students to think critically and maturely about the skills and…
As generative AI becomes increasingly integrated into higher education, its frequent errors and hallucinations, often seen as limitations, offer a unique pedagogical opportunity. By framing AI as a ``learning companion'' whose imperfect…
Context: The importance of defining learning outcomes and the planning stage for a systematic literature review. Objective: A protocol for carrying out a systematic literature review about the evidence for the tool support for the learning…
Self-evolving reasoning frameworks let LLMs improve their reasoning capabilities by iteratively generating and solving problems without external supervision, using verifiable rewards. Ideally, such systems are expected to explore a diverse…
Data selection in instruction tuning emerges as a pivotal process for acquiring high-quality data and training instruction-following large language models (LLMs), but it is still a new and unexplored research area for vision-language models…
Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gained widespread acceptance. Static strategies for scoring item difficulty rely on indirect proxy…
The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Models (SLMs) to mimic surface-level patterns rather than the…
As a new and promising approach, existing machine unlearning (MU) works typically emphasize theoretical formulations or optimization objectives to achieve knowledge removal. However, when deployed in real-world scenarios, such solutions…
We introduce a new paradigm of learning for reasoning, understanding, and prediction, as well as the scaffolding network to implement this paradigm. The scaffolding network embodies an incremental learning approach that is formulated as a…
We start out by demonstrating that an elementary learning task, corresponding to the training of a single linear neuron in a convolutional neural network, can be solved for feature spaces of very high dimensionality. In a second step,…
Meta-learning (a.k.a. learning to learn) has recently emerged as a promising paradigm for a variety of applications. There are now many meta-learning methods, each focusing on different modeling aspects of base and meta learners, but all…
With the rapid adoption of AI tools in learning contexts, it is vital to understand how these systems shape users' reading processes and cognitive engagement. We collected and analyzed text from 124 sessions with AI tools, in which students…
Curriculum Learning is the presentation of samples to the machine learning model in a meaningful order instead of a random order. The main challenge of Curriculum Learning is determining how to rank these samples. The ranking of the samples…
In humans and animals, curriculum learning -- presenting data in a curated order - is critical to rapid learning and effective pedagogy. Yet in machine learning, curricula are not widely used and empirically often yield only moderate…