In open-domain question-answering (ODQA), most existing questions require single-hop reasoning on commonsense. To further extend this task, we officially introduce open-domain multi-hop reasoning (ODMR) by answering multi-hop questions with explicit reasoning steps in open-domain setting. Recently, large language models (LLMs) have found significant utility in facilitating ODQA without external corpus. Furthermore, chain-of-thought (CoT) prompting boosts the reasoning capability of LLMs to a greater extent with manual or automated paradigms. However, existing automated methods lack of quality assurance, while manual approaches suffer from limited scalability and poor diversity, hindering the capabilities of LLMs. In this paper, we propose Self-prompted Chain-of-Thought (SP-CoT), an automated framework to mass-produce high quality CoTs of LLMs, by LLMs and for LLMs. SP-CoT introduces an automated generation pipeline of high quality ODMR datasets, an adaptive sampler for in-context CoT selection and self-prompted inference via in-context learning. Extensive experiments on four multi-hop question-answering benchmarks show that our proposed SP-CoT not only significantly surpasses the previous SOTA methods on large-scale (175B) LLMs, but also nearly doubles the zero-shot performance of small-scale (13B) LLMs. Further analysis reveals the remarkable capability of SP-CoT to elicit direct and concise intermediate reasoning steps by recalling $\sim$50\% of intermediate answers on MuSiQue-Ans dataset.

Electrostatic actuators provide a promising approach to creating soft robotic sheets, due to their flexible form factor, modular integration, and fast response speed. However, their control requires kilo-Volt signals and understanding of complex dynamics resulting from force interactions by on-board and environmental effects. In this work, we demonstrate an untethered planar five-actuator piezoelectric robot powered by batteries and on-board high-voltage circuitry, and controlled through a wireless link. The scalable fabrication approach is based on bonding different functional layers on top of each other (steel foil substrate, actuators, flexible electronics). The robot exhibits a range of controllable motions, including bidirectional crawling (up to ~0.6 cm/s), turning, and in-place rotation (at ~1 degree/s). High-speed videos and control experiments show that the richness of the motion results from the interaction of an asymmetric mass distribution in the robot and the associated dependence of the dynamics on the driving frequency of the piezoelectrics. The robot's speed can reach 6 cm/s with specific payload distribution.

Some students have been using ChatGPT, a text-based bot, to do their homework for them. Now, 22-year-old Edward Tian's new app is attracting educators working to combat AI plagiarism.

For artificial intelligence to realize its potential -- to relieve humans from mundane tasks, make life easier, and eventually invent entirely new solutions to our problems -- computers will need to surpass us at two things that we humans do pretty well: see the world around us and understand our language. "Learning to see and learning to read are the two main things we need for the computer to do to gain knowledge," said Jen Rexford, chair of Princeton's computer science department and the Gordon Y.S. Wu Professor in Engineering. "We call these fields computer vision and natural language processing. These two fields have evolved independently but our faculty are bringing them together in interesting ways." In recent years, researchers at Princeton and beyond have made major strides in these two fields, opening up rapid progress across a variety of applications.

A team of researchers at Princeton has found that human-language descriptions of tools can accelerate the learning of a simulated robotic arm that can lift and use various tools. The new research supports the idea that AI training can make autonomous robots more adaptive in new situations, which in turn improves their effectiveness and safety. By adding descriptions of a tool's form and function to the robot's training process, the robot's ability to manipulate new tools was improved. The new method is called Accelerated Learning of Tool Manipulation with Language, or ATLA. Anirudha Majumdar is an assistant professor of mechanical and aerospace engineering at Princeton and head of the Intelligent Robot Motion Lab.

This week, OpenAI granted users of its image-generating AI system, DALL-E 2, the right to use their generations for commercial projects, like illustrations for children's books and art for newsletters. DALL-E 2 "trained" on approximately 650 million image-text pairs scraped from the internet, learning from that dataset the relationships between images and the words used to describe them. But while OpenAI filtered out images for specific content (e.g. As the AI community creates open source implementations of DALL-E 2 and its predecessor, DALL-E, both free and paid services are launching atop models trained on less-carefully filtered datasets. When contacted for comment, the Pixelz.ai

ACM fellow Dana Stewart Scott, the recipient jointly with Michael Rabin of the 1976 A.M. Turing Award for the concept of nondeterministic finite automata, has made seminal contributions spanning computing science, mathematics, philosophy, automata theory, modal logic, model theory, set theory, and the theory of programming languages. After receiving a B.A. in mathematics from the University of California, Berkeley, in 1950, and a Ph.D. from Princeton University in 1958, he held faculty positions at the University of Chicago, UC Berkeley, and at Stanford, Princeton, Oxford, and Carnegie Mellon Universities. He retired as University Professor from CMU in 2003. The distinguished theoretical computer scientist Gordon Plotkin conducted a series of four oral history interviews of Scott between November 2020 and February 2021. The interviews, the transcripts and videos of which are online,a cover primarily the period leading up to the 1976 ACM A.M. Turing Award. Presented here is a condensed and highly edited version, which includes some additional post-interview material provided by Scott. I was born in 1932 in Berkeley, CA, where I am now in retirement. We lived on a farm near Susanville when I started first grade in a one-room school-house.

This week, OpenAI granted users of its image-generating AI system, DALL-E 2, the right to use their generations for commercial projects, like illustrations for children's books and art for newsletters. DALL-E 2 "trained" on approximately 650 million image-text pairs scraped from the Internet, learning from that data set the relationships between images and the words used to describe them. But while OpenAI filtered out images for specific content (e.g. As the AI community creates open source implementations of DALL-E 2 and its predecessor, DALL-E, both free and paid services are launching atop models trained on less-carefully-filtered data sets. When contacted for comment, the Pixelz.ai

Rajiv Malhotra was trained initially as a Physicist, and then as a Computer Scientist specializing in AI in the 1970s. After a successful corporate career in the US, he became an entrepreneur and founded and ran several IT companies in 20 countries. Since the early 1990s, as the founder of his non-profit Infinity Foundation (Princeton, USA), he has been researching civilizations and their engagement with technology from a historical, social sciences and mind sciences perspective. He has authored several best-selling books. Infinity Foundation has also published a 14-volume series on the History of Indian Science & Technology.

Soft robots have drawn great interest due to their ability to take on a rich range of shapes and motions, compared to traditional rigid robots. However, the motions, and underlying statics and dynamics, pose significant challenges to forming well-generalized and robust models necessary for robot design and control. In this work, we demonstrate a five-actuator soft robot capable of complex motions and develop a scalable simulation framework that reliably predicts robot motions. The simulation framework is validated by comparing its predictions to experimental results, based on a robot constructed from piezoelectric layers bonded to a steel-foil substrate. The simulation framework exploits the physics engine PyBullet, and employs discrete rigid-link elements connected by motors to model the actuators. We perform static and AC analyses to validate a single-unit actuator cantilever setup and observe close agreement between simulation and experiments for both the cases. The analyses are extended to the five-actuator robot, where simulations accurately predict the static and AC robot motions, including shapes for applied DC voltage inputs, nearly-static "inchworm" motion, and jumping (in vertical as well as vertical and horizontal directions). These motions exhibit complex non-linear behavior, with forward robot motion reaching ~1 cm/s. Our open-source code can be found at: https://github.com/zhiwuz/sfers.