Related papers: Generating Natural-Language Surgical Feedback: Fro…

Configuration optimization remains a critical bottleneck in machine learning, requiring coordinated tuning across model architecture, training strategy, feature engineering, and hyperparameters. Traditional approaches treat these dimensions…

Therapeutic dialogue is not a sequence of isolated responses: client goals, motivation, resistance, and therapeutic alliance evolve over time. Yet current LLM-based mental health dialogue systems often lack explicit mechanisms for tracking…

Adapting one's thought process based on corrective feedback is an essential ability in human learning, particularly in collaborative settings. In contrast, the current large language model training paradigm relies heavily on modeling vast,…

Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning. One possible way to help bridge this gap be to provide RL agents with richer,…

In many areas, we have well-founded insights about causal structure that would be useful to bring into our trained models while still allowing them to learn in a data-driven fashion. To achieve this, we present the new method of interchange…

Pretrained language models often do not perform tasks in ways that are in line with our preferences, e.g., generating offensive text or factually incorrect summaries. Recent work approaches the above issue by learning from a simple form of…

Incorporating automatically predicted human feedback into the process of training generative models has attracted substantial recent interest, while feedback at inference time has received less attention. The typical feedback at training…

Large language models are able to perform a task by conditioning on a few input-output demonstrations - a paradigm known as in-context learning. We show that language models can explicitly infer an underlying task from a few demonstrations…

Current text-to-video (T2V) generation models are increasingly popular due to their ability to produce coherent videos from textual prompts. However, these models often struggle to generate semantically and temporally consistent videos when…

Traditional neural network training typically follows fixed, predefined optimization recipes, lacking the flexibility to dynamically respond to instabilities or emerging training issues. In this paper, we introduce Interactive Training, an…

Generative AI and large language models hold great promise in enhancing programming education by automatically generating individualized feedback for students. We investigate the role of generative AI models in providing human tutor-style…

Videos are prominent learning materials to prepare surgical trainees before they enter the operating room (OR). In this work, we explore techniques to enrich the video-based surgery learning experience. We propose Surgment, a system that…

We tackle the question of how to scale more efficiently across the many, ever-growing stages of current LLM training pipelines. Our guiding intuition stems from the fact that the dynamics of later stages of the pipeline, e.g. post-training,…

Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or Google Assistant) are built using manually annotated data to train the different components of the system. Typically, the accuracy of the ML models in these components…

This paper focuses on the dynamic optimization of the Retrieval-Augmented Generation (RAG) architecture. It proposes a state-aware dynamic knowledge retrieval mechanism to enhance semantic understanding and knowledge scheduling efficiency…

Frozen models trained to mimic static datasets can never improve their performance. Models that can employ internet-retrieval for up-to-date information and obtain feedback from humans during deployment provide the promise of both adapting…

Natural language (NL) feedback offers rich insights into user experience. While existing studies focus on an instance-level approach, where feedback is used to refine specific examples, we introduce a framework for system-level use of NL…

In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generative models provide a consistent network architecture between…

The growing demand for cognitive remediation therapy, combined with limited speech therapist availability, has accelerated the adoption of remote rehabilitation tools. These systems generate large volumes of interaction data that are…

The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary highly across applications and domains. Meanwhile, for natural…