Related papers: Overcoming Over-Fitting in Constraint Acquisition …

In many real-world scenarios, acquiring all features of a data instance can be expensive or impractical due to monetary cost, latency, or privacy concerns. Active Feature Acquisition (AFA) addresses this challenge by dynamically selecting a…

The pretraining-finetuning paradigm has gained widespread adoption in vision tasks and other fields, yet it faces the significant challenge of high sample annotation costs. To mitigate this, the concept of active finetuning has emerged,…

Quantum architecture search (QAS) represents a fundamental challenge in quantum machine learning. Unlike previous methods that treat it as a static search process, from a perspective on QAS as an item retrieval task in vast search space, we…

We consider the task of training machine learning models with data-dependent constraints. Such constraints often arise as empirical versions of expected value constraints that enforce fairness or stability goals. We reformulate…

Enforcing complex (e.g., nonconvex) operational constraints is a critical challenge in real-world learning and control systems. However, existing methods struggle to efficiently enforce general classes of constraints. To address this, we…

While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing…

Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on individual tasks. Agents trained with Deep Reinforcement…

Supervised neural approaches are hindered by their dependence on large, meticulously annotated datasets, a requirement that is particularly cumbersome for sequential tasks. The quality of annotations tends to deteriorate with the transition…

We consider adaptive decision-making problems where an agent optimizes a cumulative performance objective by repeatedly choosing among a finite set of options. Compared to the classical prediction-with-expert-advice set-up, we consider…

Deep learning has profoundly impacted domains such as computer vision and natural language processing by uncovering complex patterns in vast datasets. However, the reliance on extensive labeled data poses significant challenges, including…

Retrieval-augmented generation (RAG) connects large language models (LLMs) to external knowledge, but single-round retrieval is often insufficient for complex multi-hop questions. To enhance search capabilities for complex tasks, most…

This paper presents a groundbreaking self-improving interference management framework tailored for wireless communications, integrating deep learning with uncertainty quantification to enhance overall system performance. Our approach…

Retrieval-Augmented Generation (RAG) is a core approach for enhancing Large Language Models (LLMs), where the effectiveness of the retriever largely determines the overall response quality of RAG systems. Retrievers encompass a multitude of…

Retriever-augmented instruction-following models are attractive alternatives to fine-tuned approaches for information-seeking tasks such as question answering (QA). By simply prepending retrieved documents in its input along with an…

This paper presents the development of a new collaborative road profile estimation and active suspension control framework in connected vehicles, where participating vehicles iteratively refine the road profile estimation and enhance…

Contact-rich manipulation plays an important role in daily human activities. However, uncertain physical parameters often pose significant challenges for both planning and control. A promising strategy is to develop policies that are robust…

Retrieve-augmented generation (RAG) frameworks have emerged as a promising solution to multi-hop question answering(QA) tasks since it enables large language models (LLMs) to incorporate external knowledge and mitigate their inherent…

Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness…

In text-based person search endeavors, data generation has emerged as a prevailing practice, addressing concerns over privacy preservation and the arduous task of manual annotation. Although the number of synthesized data can be infinite in…

Force interaction is inevitable when robots face multiple operation scenarios. How to make the robot competent in force control for generalized operations such as multi-tasks still remains a challenging problem. Aiming at the…