21 papers · ranked by Valyu relevance
Cunxi Yu, Chenhui Deng, Nathaniel Pinckney, Brucek Khailany
We present HORIZON, a self-evolving agent framework that treats hardware design as repository-level code evolution. A Markdown harness is compiled into a project pack containing domain knowledge, an executable evaluator, an acceptance predicate, and a git/runtime policy; a hands-free agent loop then evolves an isolated…
René Groh, Stefan Dendorfer, Mateo Ávila Pava, Fabio Egle + 2 more
Edge AI holds great potential for extending the use of artificial neural networks to resource-constrained edge devices, such as microcontrollers. Despite this potential, optimizing and deploying neural networks on these platforms remains challenging due to a lack of tools for hardware-specific adaptation, leading to…
Authors not listed
RNA droplets assembled from co-transcriptionally folded nanostructures have recently emerged as a promising platform for constructing protocells and minimal synthetic cell models. In these systems, a custom-designed DNA template encodes an RNA nanostar, which is produced by transcription and self-assembles into…
Jiangwei Zhang, Wen Sun, Chong Wang, Shiyao Li + 6 more
Artificial intelligence increasingly drives automated scientific discovery, yet contemporary generalist agents lack physical grounding, frequently hallucinating hardware-incompatible designs. Here, we present a physically grounded, multi-agent discovery engine that autonomously architects hardware-compliant computing…
Tingyang Chen, Shuo Lu, Kang Zhao, Weicheng Meng + 10 more
AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces…
Shweta Rana, Harpreet Singh
Müller, Steels, and Szathmáry made this timely case that evolvable AI (eAI) should be treated as a distinct class of risk because essential elements of life such as replication, heredity, variation, and selection were also created in digital systems (1). Their distinction between human-controlled “breeder” settings and…
Jakub Fil, Yulia Sandamirskaya, Hector Gonzalez, Loïc Azzalin + 17 more
| Jakub Fil1∗ | Yulia Sandamirskaya2 | Hector Gonzalez3 | Loïc Azzalin2 | |--------------------|----------------------|------------------|-----------------| | Stefan Glüge2 | Lukas Friedenstab1 | Friedrich Wolf1 | Tim Rosmeisl3 | | Matthias Lohrmann3 | Mahmoud Akl3 | Khaleel Khan4 | Leonie Wolf1 | | Kristin Richter1 |…
Authors not listed
This comprehensive review examines the evolution of autonomous materials synthesis laboratories that integrate artificial intelligence with advanced robotics to accelerate discovery. Traditional materials development pipelines typically require 10-20 years, but self-driving laboratories (SDLs) and Materials…
Florian Frank, Stefan Katzenbeisser
Physical Unclonable Functions (PUFs) are widely recognized for deriving strong cryptographic keys from inherent manufacturing variations in hardware. A popular class of PUFs is extracted from memory modules already integrated into computing systems, offering a cost-efficient method for generating strong cryptographic…
Jose Balbuena, Julio Sinche, Diego Quiroz, Diego Arce + 1 more
Title: Graphical abstract
Ivan Kondratyev, Weinan Sun
AI coding assistants excel at software tasks but lack structured access to laboratory hardware, the physical instruments that define experimental science. We present Ataraxis, an open-source framework that provides hardware control capabilities spanning camera acquisition, microcontroller communication, precision…
Cheng Siong Chin, Jianhua Zhang, Mohan Venkateshkumar
Autonomous systems inevitably age, yet their artificial intelligence typically assumes hardware remains in its original condition. Batteries degrade, sensors drift, processors accumulate timing errors, and memory reliability declines, creating a growing mismatch between assumed and actual capability. This can lead to…
Authors not listed
Despite the promise of self-driving laboratories to accelerate discovery, their widespread implementation is hindered by prohibitive cost and technical complexity. We introduce BrickSDLab, a fully functional self-driving lab platform built entirely from LEGO® components, designed to bridge this accessibility gap.…
Authors not listed
The emergence of affordable and reliable 3D printers has enabled laboratories to optimize setups, print custom parts, accelerate research, and rapidly prototype. A new movement has emerged in the past decade, where 3D printers are repurposed as laboratory-specific robots. There are three distinct approaches in the…
Aedan Brown, Sarah Datta, Pankaj Mehta, Brian Cleary
Population genetics has been successful in explaining how drift, selection, and mutation shape allele frequencies. However, we still lack an understanding of how biological and evolutionary constraints arising from genotype-phenotype maps shape evolutionary dynamics. To explore this question, we developed a new…
Alejandro Von Chong, Salvador Vargas, Jean-François Duhé, Dorindo Cárdenas
Title: Graphical abstract
Adelin Roty, Jan Tobias Mühlberg, Jean-François Determe
An estimated 5.3 billion mobile phones became electronic waste in 2022. Many of these devices can be repurposed and used in different contexts to extend their lifetime and to reduce ecological impacts. An often overlooked aspect of smartphone reuse is cybersecurity: these devices embed hardware-backed security…
Authors not listed
Solubility is the maximum amount of solutes that can dissolve in a certain amount of solvent at a certain temperature, and it is significant in battery electrolyte research since it confines the design space. Thus, solubility measurement is a critical constraint on running self-driving labs for battery electrolyte…
Changyu Zhao, Yohan Beugin, Jean-Charles Noirot Ferrand, Quinn Burke + 2 more
Dynamic program analysis is invaluable for malware detection, debugging, and performance profiling. However, software-based instrumentation incurs high overhead and can be evaded by antianalysis techniques. In this paper, we propose LibIHT, a hardwareassisted tracing framework that leverages on-CPU branch tracing…
Brian P. Waldron, Eliza Tarimo, Palash Sashittal, Noel Naughton + 2 more
Thermal physiological traits such as body temperature often show surprisingly slow evolutionary rates over macroevolutionary time, despite apparent lability at microevolutionary time scales. While long-term stabilizing selection may slow rates of thermal evolution, we propose an alternative hypothesis from a bottom-up…
Maxwell B. Madden, Mahee Khatri, Arnav Mohanty, Disha Prasad + 2 more
Head-fixed behavior in rodents is a foundational technique in systems neuroscience which enables use of sophisticated imaging techniques in combination with animal behavior. However, accessibility of head-fixed behavior techniques is limited. Animal training consumes a large amount of experimenter labor and commercial…