相关论文: Recursive Learning-Based Virtual Buffering for Ana…

Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or…

Developing a single foundation model with the capability to excel across diverse tasks has been a long-standing objective in the field of artificial intelligence. As the wave of general-purpose foundation models sweeps across various…

Retrieval-Augmented Generation (RAG) improves reliability of large language models by incorporating external knowledge, but the retrieval process can introduce bias that propagates to generated outputs. This issue is particularly…

High-level autonomous driving requires motion planners capable of modeling multimodal future uncertainties while remaining robust in closed-loop interactions. Although diffusion-based planners are effective at modeling complex trajectory…

This study addresses the rebalancing of empty modular transit pods between scheduled service trips in fixed-route bus systems. A two-stage hierarchical optimization framework is proposed. The first stage determines the minimum fleet size…

Reinforcement learning has been applied in operation research and has shown promise in solving large combinatorial optimization problems. However, existing works focus on developing neural network architectures for certain problems. These…

Conventional model upgrades for visual search systems require offline refresh of gallery features by feeding gallery images into new models (dubbed as "backfill"), which is time-consuming and expensive, especially in large-scale…

Normalizing Flows (NFs) are a class of generative models distinguished by a mathematically invertible architecture, where the forward pass transforms data into a latent space for density estimation, and the reverse pass generates new…

Facility location problems on graphs are ubiquitous in real world and hold significant importance, yet their resolution is often impeded by NP-hardness. Recently, machine learning methods have been proposed to tackle such classical…

Reinforcement Learning (RL) has shown exceptional performance across various applications, enabling autonomous agents to learn optimal policies through interaction with their environments. However, traditional RL frameworks often face…

Visual place recognition (VPR) is a key issue for robotics and autonomous systems. For the trade-off between time and performance, most of methods use the coarse-to-fine hierarchical architecture, which consists of retrieving top-N…

Hierarchical multi-robot exploration commonly decouples frontier allocation from local navigation, which can make the system brittle in dense and dynamic environments. Because the allocator lacks direct awareness of execution difficulty,…

This paper addresses a fundamental problem of visuomotor policy learning for robotic manipulation: how to enhance robustness in out-of-distribution execution errors or dynamically re-routing trajectories, where the model relies solely on…

Reinforcement learning post-training has substantially improved the reasoning accuracy of vision-language models, yet the resulting policies remain poorly calibrated. Terminal correctness rewards provide no gradient that penalizes confident…

State-of-the-art reinforcement learning algorithms mostly rely on being allowed to directly interact with their environment to collect millions of observations. This makes it hard to transfer their success to industrial control problems,…

Global routing has been a historically challenging problem in electronic circuit design, where the challenge is to connect a large and arbitrary number of circuit components with wires without violating the design rules for the printed…

Relative pose estimation is fundamental for SLAM, visual localization, and 3D reconstruction. Existing Relative Pose Regression (RPR) methods face a key trade-off: feature-matching pipelines achieve high accuracy but block gradient flow via…

Reinforcement learning (RL) is a foundation of learning in biological systems and provides a framework to address numerous challenges with real-world artificial intelligence applications. Efficient implementations of RL techniques could…

Large language models (LLMs) commonly struggle with specialized or emerging topics which are rarely seen in the training corpus. Graph-based retrieval-augmented generation (GraphRAG) addresses this by structuring domain knowledge as a graph…

Microservice architectures enable scalable cloud-native applications; however, the distributed nature of these systems complicates the maintenance of strict Service Level Objectives. Accurately predicting window-level P95 tail latency…