Related papers: What Objective Does Self-paced Learning Indeed Opt…
Adding constraint support in Machine Learning has the potential to address outstanding issues in data-driven AI systems, such as safety and fairness. Existing approaches typically apply constrained optimization techniques to ML training,…
Self supervised learning (SSL) is a machine learning paradigm where models learn to understand the underlying structure of data without explicit supervision from labeled samples. The acquired representations from SSL have demonstrated…
Federated Learning (FL) is a novel, multidisciplinary Machine Learning paradigm where multiple clients, such as mobile devices, collaborate to solve machine learning problems. Initially introduced in Kone{\v{c}}n{\'y} et al. (2016a,b);…
Over the past few years, self-attention is shining in the field of deep learning, especially in the domain of natural language processing(NLP). Its impressive effectiveness, along with ubiquitous implementations, have aroused our interest…
Conventional machine learning (ML) relies heavily on manual design from machine learning experts to decide learning tasks, data, models, optimization algorithms, and evaluation metrics, which is labor-intensive, time-consuming, and cannot…
Machine learning models are increasingly being utilized across various fields and tasks due to their outstanding performance and strong generalization capabilities. Nonetheless, their success hinges on the availability of large volumes of…
Automated optimization modeling via Large Language Models (LLMs) has emerged as a promising approach to assist complex human decision-making. While post-training has become a pivotal technique to enhance LLMs' capabilities in this domain,…
State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss.…
Optimization in machine learning typically deals with the minimization of empirical objectives defined by training data. However, the ultimate goal of learning is to minimize the error on future data (test error), for which the training…
Safe reinforcement learning (SafeRL) is a prominent paradigm for autonomous driving, where agents are required to optimize performance under strict safety requirements. This dual objective creates a fundamental tension, as overly…
In this work, we introduce a learning model designed to meet the needs of applications in which computational resources are limited, and robustness and interpretability are prioritized. Learning problems can be formulated as constrained…
Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs…
Learning to improve AUC performance is an important topic in machine learning. However, AUC maximization algorithms may decrease generalization performance due to the noisy data. Self-paced learning is an effective method for handling noisy…
Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanisms: self-reflection for context updates, and reinforcement…
While self-supervised learning has been shown to benefit a number of vision tasks, existing techniques mainly focus on image-level manipulation, which may not generalize well to downstream tasks at patch or pixel levels. Moreover, existing…
Contrastive learning, especially self-supervised contrastive learning (SSCL), has achieved great success in extracting powerful features from unlabeled data. In this work, we contribute to the theoretical understanding of SSCL and uncover…
Supervised learning is classically formulated as training a model to minimize a fixed loss function over a fixed distribution, or task. However, an emerging paradigm instead views model training as extracting enough information from data so…
Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a helpful assistant. At the same time, SFT may harm the fundamental capabilities of an LLM,…
We study zero-shot instance navigation, in which the agent navigates to a specific object without using object annotations for training. Previous object navigation approaches apply the image-goal navigation (ImageNav) task (go to the…
Large Language Models (LLMs) have become pivotal in advancing the field of artificial intelligence, yet their immense sizes pose significant challenges for both fine-tuning and deployment. Current post-training pruning methods, while…