Related papers: Teaching by Failure: Counter-Example-Driven Curric…

Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks…

Designing generalizable agents capable of adapting to diverse embodiments has achieved significant attention in Reinforcement Learning (RL), which is critical for deploying RL agents in various real-world applications. Previous…

We present a novel framework for augmenting data sets for machine learning based on counterexamples. Counterexamples are misclassified examples that have important properties for retraining and improving the model. Key components of our…

Curriculum learning techniques are a viable solution for improving the accuracy of automatic models, by replacing the traditional random training with an easy-to-hard strategy. However, the standard curriculum methodology does not…

Transformers have demonstrated remarkable in-context learning (ICL) capabilities, adapting to new tasks by simply conditioning on demonstrations without parameter updates. Compelling empirical and theoretical evidence suggests that ICL, as…

In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training.…

Curriculum learning is a widely adopted training strategy in natural language processing (NLP), where models are exposed to examples organized by increasing difficulty to enhance learning efficiency and performance. However, most existing…

Curriculum reinforcement learning (CRL) improves the learning speed and stability of an agent by exposing it to a tailored series of tasks throughout learning. Despite empirical successes, an open question in CRL is how to automatically…

We provide theoretical investigation of curriculum learning in the context of stochastic gradient descent when optimizing the convex linear regression loss. We prove that the rate of convergence of an ideal curriculum learning method is…

Counterfactual explanation is a form of interpretable machine learning that generates perturbations on a sample to achieve the desired outcome. The generated samples can act as instructions to guide end users on how to observe the desired…

Deep reinforcement learning (RL) has shown great empirical successes, but suffers from brittleness and sample inefficiency. A potential remedy is to use a previously-trained policy as a source of supervision. In this work, we refer to these…

Recent advances in self-evolution video understanding frameworks have demonstrated the potential of autonomous learning without human annotations. However, existing methods often suffer from weakly controlled optimization and uncontrolled…

Continual learning (CL) learns a sequence of tasks incrementally with the goal of achieving two main objectives: overcoming catastrophic forgetting (CF) and encouraging knowledge transfer (KT) across tasks. However, most existing techniques…

Recent work on Grammatical Error Correction (GEC) has highlighted the importance of language modeling in that it is certainly possible to achieve good performance by comparing the probabilities of the proposed edits. At the same time,…

Complex Verilog Design Problems (CVDP) challenge hardware LLM agents because solving them requires localizing verifier-relevant RTL, testbenches, include paths, and build dependencies inside large repository snapshots, making precise edits,…

Machine Reading Comprehension (MRC) reveals the ability to understand a given text passage and answer questions based on it. Existing research works in MRC rely heavily on large-size models and corpus to improve the performance evaluated by…

Hyperdimensional computing (HDC) has become popular for light-weight and energy-efficient machine learning, suitable for wearable Internet-of-Things (IoT) devices and near-sensor or on-device processing. HDC is computationally less complex…

Large vision-language models (VLMs) achieve strong benchmark performance, but controlling their behavior through instruction tuning remains difficult. Reducing the budget of instruction tuning dataset often causes regressions, as heuristic…

Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) trained on a given instruction dataset. Curriculum learning as a typical data organization strategy has shown preliminary effectiveness in…

We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms by means of a control strategy with limited knowledge of the system model. By tutoring the learning process, the…