相关论文: AI capabilities can be significantly improved with…

Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy fine-tuning data at the expense of the high-entropy pretraining distribution.…

This paper analyzes and compares 11 different proposals for building safe advanced AI under the current machine learning paradigm, including major contenders such as iterated amplification, AI safety via debate, and recursive reward…

Semi-supervised learning provides a solution to reduce the dependency of machine learning on labeled data. As one of the efficient semi-supervised techniques, self-training (ST) has received increasing attention. Several advancements have…

Automatic machine learning performs predictive modeling with high performing machine learning tools without human interference. This is achieved by making machine learning applications parameter-free, i.e. only a dataset is provided while…

Post-training has become effective for high-level generation, but its role in low-level vision remains underexplored. Existing image restoration methods often rely on fixed pixel-wise fitting to ground-truth images, which can lead to…

In human-in-the-loop reinforcement learning or environments where calculating a reward is expensive, the costly rewards can make learning efficiency challenging to achieve. The cost of obtaining feedback from humans or calculating expensive…

Recent image inpainting methods have shown promising results due to the power of deep learning, which can explore external information available from the large training dataset. However, many state-of-the-art inpainting networks are still…

Recent progress in large-scale language models has enabled breakthroughs in previously intractable computer programming tasks. Prior work in meta-learning and neural architecture search has led to substantial successes across various task…

AI-assisted research is crossing a threshold: fully automated systems can now generate research papers for as little as $15, while long-horizon agents can execute experiments, draft manuscripts, and simulate critique with minimal human…

Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-training and argue that existing sequence-level reward-shaping…

Neural network subgrid stress models often have a priori performance that is far better than the a posteriori performance, leading to neural network models that look very promising a priori completely failing in a posteriori Large Eddy…

In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet it often comes at the cost of decreased AI performance in areas of human strengths. This can…

Speech enhancement using artificial neural networks aims to remove noise from noisy speech signals while preserving the speech content. However, speech enhancement networks often introduce distortions to the speech signal, referred to as…

Pruning is an effective way to reduce the huge inference cost of Transformer models. However, prior work on pruning Transformers requires retraining the models. This can add high training cost and high complexity to model deployment, making…

Despite the superior performance, it is challenging to deploy foundation models or large language models (LLMs) due to their massive parameters and computations. While pruning is a promising technique to reduce model size and accelerate the…

When training artificial intelligence for games encompassing multiple roles, the development of a generalized model capable of controlling any character within the game presents a viable option. This strategy not only conserves…

Our goal is to understand how post-training methods, such as fine-tuning, alignment, and unlearning, modify language model behavior and representations. We are particularly interested in the brittle nature of these modifications that makes…

Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, preference alignment, and multi-step reasoning. Reinforcement learning with verifiable rewards…

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

Fine-tuning large pre-trained foundation models, such as the 175B GPT-3, has attracted more attention for downstream tasks recently. While parameter-efficient fine-tuning methods have been proposed and proven effective without retraining…