Search Results

As a non-contact method, eye-tracking data can be used to diagnose people with Autism Spectrum Disorder (ASD) by comparing the differences of eye movements between ASD and healthy people. However, existing works mainly employ a simple free-viewing ...

In large-scale recommendation systems, modeling long-term user interests is progressively gaining attention among researchers and practitioners. Existing work, such as SIM and TWIN, typically employs a two-stage approach to model long-term user behavior ...

We argue that auto-regressive LLMs cannot, by themselves, do planning or self-verification (which is after all a form of reasoning), and shed some light on the reasons for misunderstandings in the literature. We also argue that LLMs should be viewed as ...

When engaging in collaborative tasks with unknown team members, humans demonstrate the ability to predict the behavior of their partners and adapt to it. Autonomous agents do not exhibit such adaptability, often struggling to integrate with new partners ...

Our work aims at efficiently leveraging ambiguous demonstrations for the training of a reinforcement learning (RL) agent. An ambiguous demonstration can usually be interpreted in multiple ways, which severely hinders the RL agent from learning stably and ...

There is a growing interest in applying pre-trained large language models (LLMs) to planning problems. However, methods that use LLMs directly as planners are currently impractical due to several factors, including limited correctness of plans, strong ...

Life-long user behavior modeling, i.e., extracting a user's hidden interests from rich historical behaviors in months or even years, plays a central role in modern CTR prediction systems. Conventional algorithms mostly follow two cascading stages: a ...

• Multi-contrast learning framework for WSSS with only image-level labels.
• Novel ...

Weakly supervised semantic segmentation (WSSS) has gained significant popularity as it relies only on weak labels such as image level annotations rather than the pixel level annotations required by supervised semantic segmentation (SSS)...

Large adjusting camera is an important facility of modern power grid, its own operation must be stable enough, but manual can not control it comprehensively, so it needs to use incremental PID control algorithm to carry out automatic control. This ...

Human explanation (e.g., in terms of feature importance) has been recently used to extend the communication channel between human and agent in interactive machine learning. Under this setting, human trainers provide not only the ground truth but also ...

Vehicle-to-everything (V2X) communication in vehicular ad hoc network (VANET) has emerged as a crucial component in advanced Intelligent Transport System (ITS) for information transmission and vehicular communication. One of the vital ...

Conventional works that learn grasping affordance from demonstrations need to explicitly predict grasping configurations, such as gripper approaching angles or grasping preshapes. Classic motion planners could then sample trajectories by using such ...

Traffic congestion has become one of the most serious contemporary city issues as it leads to unnecessary high energy consumption, air pollution and extra traveling time. During the past decade, many optimization algorithms have been ...

Display Omitted

• A novel deep reinforcement learning method for real-time vehicle navigation.
• ...

In recent content delivery mechanisms, popular contents tend to be placed closer to the users for better delivery performance and lower network resource occupation. Caching mechanisms in Content Delivery Networks (CDN), Mobile Edge Clouds (MECs) and fog ...

Virtualization technology adds great opportunities and challenges to the cloud computing paradigm. Resource management can be efficiently enhanced by employing Live Virtual Machine Migration (LVMM) techniques. Based on the literature of LVMM ...

Software Product Line Engineering (SPLE) has drawn large amounts of attention during the last two decades as it offers the benefits of reducing cost and time to market by reusing requirements and components. Recently, more and more large scale industries ...

Provision of instantaneous, mobile and dependable communications in military and safety-critical scenarios must overcome certain wireless network issues: lack of reliable existing infrastructure, immutability of mission-critical protocols and ...

This paper proposes a dynamic arrival process to represent a typical TCP source in Queueing theory performance modeling. This process utilises a novel time-dependant statistical calculation approach, which modifies and extends the traditional method of ...

An extensive body of research has established the efficacy of computer-assisted language learning CALL in developing interaction in the field of language education. Aiming to offer Chinese English-as-a-foreignlanguage EFL teachers more detailed ...

The complex interactions inherent in mobile, dynamic systems require a representative model of node movement properties. Dynamic systems proposed within industry, particularly in the military domain, have a requirement for dependable communication and ...