Related papers: Framework for On the Fly Input Refinement for Deep…

Large language models (LLMs) are increasingly used in decision-making contexts, but when they present answers without signaling low confidence, users may unknowingly act on erroneous outputs. Prior work shows that LLMs maintain internal…

Many engineering organizations are reimplementing and extending deep neural networks from the research community. We describe this process as deep learning model reengineering. Deep learning model reengineering - reusing, reproducing,…

As large-scale pre-trained foundation models continue to expand in size and capability, efficiently adapting them to specific downstream tasks has become increasingly critical. Despite substantial progress, existing adaptation approaches…

We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve…

Augmenting large language models (LLMs) with external tools is a promising approach to enhance their capabilities, especially for complex tasks. Synthesizing tool-use data through real-world simulations is an effective way to achieve this.…

Deep reinforcement learning has shown remarkable success in the past few years. Highly complex sequential decision making problems have been solved in tasks such as game playing and robotics. Unfortunately, the sample complexity of most…

Although Deep Reinforcement Learning (DRL) has achieved notable success in numerous robotic applications, designing a high-performing reward function remains a challenging task that often requires substantial manual input. Recently, Large…

Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as possible randomly selected from large-scale web corpora. While…

The trade-off between accuracy and interpretability has long been a challenge in machine learning (ML). This tension is particularly significant for emerging interpretable-by-design methods, which aim to redesign ML algorithms for…

While neural models show remarkable accuracy on individual predictions, their internal beliefs can be inconsistent across examples. In this paper, we formalize such inconsistency as a generalization of prediction error. We propose a…

Effective training of deep neural networks can be challenging, and there remain many open questions on how to best learn these models. Recently developed methods to improve neural network training examine teaching: providing learned…

In this paper, we present an Adaptive Ensemble Learning framework that aims to boost the performance of deep neural networks by intelligently fusing features through ensemble learning techniques. The proposed framework integrates ensemble…

Deep reinforcement learning (DRL) has proven extremely useful in a large variety of application domains. However, even successful DRL-based software can exhibit highly undesirable behavior. This is due to DRL training being based on…

With the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory…

Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific…

Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of…

Reinforcement learning systems require good representations to work well. For decades practical success in reinforcement learning was limited to small domains. Deep reinforcement learning systems, on the other hand, are scalable, not…

Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…

Compared with traditional deep learning techniques, continual learning enables deep neural networks to learn continually and adaptively. Deep neural networks have to learn new tasks and overcome forgetting the knowledge obtained from the…

For certain industrial control applications an explicit function capturing the nontrivial trade-off between competing objectives in closed loop performance is not available. In such scenarios it is common practice to use the human innate…