Related papers: The Reflexive Integrated Information Unit: A Diffe…
Models capable of "thinking with images" by dynamically grounding their reasoning in visual evidence represent a major leap in multimodal AI. However, replicating and advancing this ability is non-trivial, with current methods often trapped…
In this letter, we investigate the discrete phase shift design of the intelligent reflecting surface (IRS) in a time division duplexing (TDD) multi-user multiple input multiple output (MIMO) system.We modify the design of deep reinforcement…
An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been…
In this paper, we present a novel neural network for MIMO symbol detection. It is motivated by several important considerations in wireless communication systems; permutation equivariance and a variable number of users. The neural detector…
This paper presents a novel dual-functional hybrid Reconfigurable Intelligent Surface (RIS) for simultaneous sensing and reconfigurable reflections. We design a novel hybrid unit cell featuring dual elements, which share the same phase…
Transformer-based models have gained significant traction in sequential recommender systems (SRSs) for their ability to capture user-item interactions effectively. However, these models often suffer from high computational costs and slow…
Reconfigurable Intelligent Surface (RIS) is one of the promising techniques for 6G wireless communications, and recently has also been shown to be able to improve secure communications. However, there is a "double fading" effect in the…
Reconfigurable intelligent surface (RIS) has been deemed as one of potential components of future wireless communication systems because it can adaptively manipulate the wireless propagation environment with low-cost passive devices.…
Bistatic backscatter communication (BackCom) allows passive tags to transmit over extended ranges, but at the cost of having carrier emitters either transmitting at high powers or being deployed very close to tags. In this paper, we examine…
Motivated by the growing theoretical understanding of neural networks that employ the Rectified Linear Unit (ReLU) as their activation function, we revisit the use of ReLU activation functions for learning implicit neural representations…
Recent advancements in Graphical User Interface (GUI) agents have predominantly focused on training paradigms like supervised fine-tuning (SFT) and reinforcement learning (RL). However, the challenge of high-dynamic GUI environments remains…
Quantifying integrated information is a leading approach towards building a fundamental theory of consciousness. Integrated Information Theory (IIT) has gained attention in this regard due to its theoretically strong framework. However, it…
By moving from massive antennas to antenna surfaces for software-defined wireless systems, the reconfigurable intelligent surfaces (RISs) rely on arrays of unit cells to control the scattering and reflection profiles of signals, mitigating…
In this paper, we present a novel approach to modeling long-term dependencies in sequential data by introducing a gated recurrent unit (GRU) with a weighted time-delay feedback mechanism. Our proposed model, named $\tau$-GRU, is a…
We describe a framework of hybrid cognition by formulating a hybrid cognitive agent that performs hierarchical active inference across a human and a machine part. We suggest that, in addition to enhancing human cognitive functions with an…
Understanding an agent's goals from its behavior is fundamental to aligning AI systems with human intentions. Existing goal recognition methods typically rely on an optimal goal-oriented policy representation, which may differ from the…
Inverse reinforcement learning (IRL) recovers reward functions from observed behavior, yet traditional methods assume a single stationary reward that cannot capture goal switching within an episode. Recent multi-intention IRL methods…
The rapid adoption of generative artificial intelligence (AI) is accelerating content creation and modification. For example, variations of a given content, be it text or images, can be created almost instantly and at a low cost. This will…
A potential candidate technology for the development of future 6G networks has been recognized as Reconfigurable Intelligent Surface (RIS). However, due to the variation in radio link quality, traditional passive RISs only accomplish a…
We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commit to a wrong approach early and exhaust the step budget, the post-failure trajectory contains the…