相关论文: OPERA: An Agent for Image Restoration with End-to-…
This paper presents the AWKWARD architecture for the development of hybrid agents in Multi-Agent Systems. AWKWARD agents can have their plans re-configured in real time to align with social role requirements under changing environmental and…
Prompt-based all-in-one image restoration (IR) frameworks have achieved remarkable performance by incorporating degradation-specific information into prompt modules. Nevertheless, handling the complex and diverse degradations encountered in…
Combinatorial optimization problems involving multiple agents are notoriously challenging due to their NP-hard nature and the necessity for effective agent coordination. Despite advancements in learning-based methods, existing approaches…
Existing unified methods typically treat multi-degradation image restoration as a multi-task learning problem. Despite performing effectively compared to single degradation restoration methods, they overlook the utilization of commonalities…
Object rearrangement is a fundamental problem in robotics with various practical applications ranging from managing warehouses to cleaning and organizing home kitchens. While existing research has primarily focused on single-agent…
In real-world scenarios, image impairments often manifest as composite degradations, presenting a complex interplay of elements such as low light, haze, rain, and snow. Despite this reality, existing restoration methods typically target…
Although multi-agent systems based on large language models show strong capabilities on multiple tasks, they are still limited by high computational overhead, information loss, and robustness. Inspired by ResNet's residual learning, we…
Recently, the joint design of optical systems and downstream algorithms is showing significant potential. However, existing rays-described methods are limited to optimizing geometric degradation, making it difficult to fully represent the…
Role-playing agents (RPAs) require balancing multiple objectives, such as instruction following, persona consistency, and stylistic fidelity, which are not always perfectly aligned across different dimensions. While prior work has primarily…
With the rapid advancement of commercial multi-modal models, image editing has garnered significant attention due to its widespread applicability in daily life. Despite impressive progress, existing image editing systems, particularly…
Machine reading comprehension (MRC) that requires discrete reasoning involving symbolic operations, e.g., addition, sorting, and counting, is a challenging task. According to this nature, semantic parsing-based methods predict interpretable…
Reinforcement Learning, a machine learning framework for training an autonomous agent based on rewards, has shown outstanding results in various domains. However, it is known that learning a good policy is difficult in a domain where…
We present a proximal policy optimization (PPO) agent trained through curriculum learning (CL) principles and meticulous reward engineering to optimize a real-world high-throughput waste sorting facility. Our work addresses the challenge of…
Negotiation requires dynamically balancing self-interest and cooperation within the flow of conversation to maximize one's own utility. Yet, existing agents struggle due to bounded rationality in human data, low adaptability to counterpart…
An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-evaluate cycles. Despite its relevance, the community lacks a systematic understanding of coding…
Preserving cultural heritage is of paramount importance. In the domain of art restoration, developing a computer vision model capable of effectively restoring deteriorated images of art pieces was difficult, but now we have a good computer…
Conservatism has led to significant progress in offline reinforcement learning (RL) where an agent learns from pre-collected datasets. However, as many real-world scenarios involve interaction among multiple agents, it is important to…
Offline policy evaluation (OPE) allows us to evaluate and estimate a new sequential decision-making policy's performance by leveraging historical interaction data collected from other policies. Evaluating a new policy online without a…
This paper presents a new regularization approach -- termed OpReg-Boost -- to boost the convergence and lessen the asymptotic error of online optimization and learning algorithms. In particular, the paper considers online algorithms for…
When attempting to recover functions from observational data, one naturally seeks to do so in an optimal manner with respect to some modeling assumption. With a focus put on the worst-case setting, this is the standard goal of Optimal…