Related papers: Input-Envelope-Output: Auditable Generative Music …
The paradigm of learning from automatic annotations driven by pre-trained experts and Foundation Models dominates data-hungry applications. However, it introduces a critical challenge: model-induced label noise. Unlike stochastic noise in…
Neurodiverse learners often require reading supports, yet increasing scaffold richness can sometimes overload attention and working memory rather than improve comprehension. Grounded in the Construction-Integration model and a contingent…
Audio and music generation based on flexible multimodal control signals is a widely applicable topic, with the following key challenges: 1) a unified multimodal modeling framework, and 2) large-scale, high-quality training data. As such, we…
The channel state information (CSI) of an eavesdropper is crucial for physical layer security (PLS) design, but it is difficult to obtain due to the passive and non-cooperative nature of the eavesdropper. To this end, integrated sensing and…
Traditional acoustic environment classification relies on: i) classical signal processing algorithms, which are unable to extract meaningful representations of high-dimensional data; or on ii) supervised learning, limited by the…
Vibe coding produces correct, executable code at speed, but leaves no record of the structural commitments, dependencies, or evidence behind it. Reviewers cannot determine what invariants were assumed, what changed, or why a regression…
Advances in semiconductor technology are contributing to the increasing complexity in the design of embedded systems. Architectures with novel techniques such as evolvable nature and autonomous behavior have engrossed lot of attention. This…
As Artificial General Intelligence (AGI) becomes increasingly integrated into various facets of human life, ensuring the safety and ethical alignment of such systems is paramount. Previous studies primarily focus on single-modality threats,…
We present a design framework to induce stable oscillations through mixed feedback control. We provide conditions on the feedback gain and on the balance between positive and negative feedback contributions to guarantee robust oscillations.…
Safe planning of an autonomous agent in interactive environments -- such as the control of a self-driving vehicle among pedestrians -- poses a major challenge as the behavior of the environment is unknown and reactive to the behavior of the…
The integration of continuous data from built-in sensors and Large Language Models (LLMs) has fueled a surge of "Sensor-Fused LLM agents" for personal health and well-being support. While recent breakthroughs have demonstrated the technical…
Recent advances in video diffusion models have unlocked new potential for realistic audio-driven talking video generation. However, achieving seamless audio-lip synchronization, maintaining long-term identity consistency, and producing…
Generative spoken language models produce speech in a wide range of voices, prosody, and recording conditions, seemingly approaching the diversity of natural speech. However, the extent to which generated speech is acoustically diverse…
This letter investigates the robust beamforming design for a near-field secure integrated sensing and communication (ISAC) system with multiple communication users (CUs) and targets, as well as multiple eavesdroppers. Taking into account…
Voice biometric systems can exhibit sex-related performance gaps even when overall verification accuracy is strong. We attribute these gaps to two practical mechanisms: (i) demographic shortcut learning, where speaker classification…
One of the key challenges faced by autistic children is understanding social affordances in complex environments, which further impacts their ability to respond appropriately to social signals. In traffic scenarios, this impairment can even…
Many engineering problems require identifying feasible domains under implicit constraints. One example is finding acceptable car body styling designs based on constraints like aesthetics and functionality. Current active-learning based…
Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend…
Evaluating and optimising human comfort within the built environment is challenging due to the large number of physiological, psychological and environmental variables that affect occupant comfort preference. Human perception could be…
Autonomous AI systems reveal foundational limitations in deterministic, human-authored computing architectures. This paper presents Cognitive Silicon: a hypothetical full-stack architectural framework projected toward 2035, exploring a…