Are there two Chilean marked gecko species, or 11? Breakthroughs, discoveries, and DIY tips sent every weekday. The Chilean marked geckos that call Chile's Atacama Desert home have proved annoyingly difficult to classify. While one might assume that different species simply look from each other, that's not always the case. Currently, Chilean marked geckos, also known as Garthia geckos, officially consist of two species-- and . However, different researchers have proposed more or even suggested that only one species exists within the genus .

The declarative specification is closer to the problem description than the reasoning steps are, so the LLM can parse it out of the description more accurately. Furthermore, by offloading the actual reasoning task to an automated theorem prover, our approach can guarantee the correctness of the answer with respect to the parsed specification and avoid planning errors in the solving process.

Large language models' significant advances in capabilities are accompanied by significant increases in inference costs. Model routing is a simple technique for reducing inference cost, wherein one maintains a pool of candidate LLMs, and learns to route each prompt to the smallest feasible LLM. Existing works focus on learning a router for a fixed pool of LLMs. In this paper, we consider the problem of dynamic routing, where new, previously unobserved LLMs are available at test time. We propose a new approach to this problem that relies on representing each LLM as a feature vector, derived based on predictions on a set of representative prompts. Based on this, we detail two effective strategies, relying on cluster-based routing and a learned cluster map respectively. We prove that these strategies are estimates of a theoretically optimal routing rule, and provide an excess risk bound to quantify their errors. Experiments on a range of public benchmarks show the effectiveness of the proposed strategies in routing amongst more than 30 unseen LLMs.

We introduce GECKO, a bilingual large language model (LLM) optimized for Korean and English, along with programming languages. GECKO is pretrained on the balanced, high-quality corpus of Korean and English employing LLaMA architecture. In this report, we share the experiences of several efforts to build a better data pipeline for the corpus and to train our model. GECKO shows great efficiency in token generations for both Korean and English, despite its small size of vocabulary. We measure the performance on the representative benchmarks in terms of Korean, English and Code, and it exhibits great performance on KMMLU (Korean MMLU) and modest performance in English and Code, even with its smaller number of trained tokens compared to English-focused LLMs. GECKO is available to the open-source community under a permissive license. We hope our work offers a research baseline and practical insights for Korean LLM research. The model can be found at: https://huggingface.co/kifai/GECKO-7B

Text embedding models represent natural language as dense vectors, positioning semantically similar text near each other within the embedding space (Gao et al., 2021; Le and Mikolov, 2014; Reimers and Gurevych, 2019). These embeddings are commonly used for a wide range of downstream tasks including document retrieval, sentence similarity, classification, and clustering (Muennighoff et al., 2023). Instead of building separate embedding models for each downstream task, recent efforts seek to create a single embedding model supporting many tasks. The recent development of general-purpose text embedding models presents a challenge: these models require large amounts of training data to comprehensively cover desired domains and skills. Recent embedding efforts have focused on using extensive collections of training examples (Li et al., 2023; Wang et al., 2022).

Neural Cellular Automata (NCAs) are a model of morphogenesis, capable of growing two-dimensional artificial organisms from a single seed cell. In this paper, we show that NCAs can be trained to respond to signals. Two types of signal are used: internal (genomically-coded) signals, and external (environmental) signals. Signals are presented to a single pixel for a single timestep. Results show NCAs are able to grow into multiple distinct forms based on internal signals, and are able to change colour based on external signals. Overall these contribute to the development of NCAs as a model of artificial morphogenesis, and pave the way for future developments embedding dynamic behaviour into the NCA model. Code and target images are available through GitHub: https://github.com/jstovold/ALIFE2023

Flying geckos are able to use their tails to stabilise their landings after crashing into trees at speeds of up to 13 miles per hour, a new study has revealed. A drone based on the remarkable crash landing capabilities of the small lizard opens the door to future airborne robots that can land on walls or upside down, according to the developers at the Max Planck Institute for Intelligent Systems in Stuttgart. They discovered that the colourful creatures use their tail to stabilise themselves after gliding head first into a tree trunk, stopping them falling to the ground. Corresponding author Dr Ardian Jusufi said structures similar to gecko tails could stabilise drones during a landing on a vertical surface. This could lead to robots that can land in inaccessible places, helping search and rescue after a landslide or building collapse, or during military operations, they said. Geckos' climbing abilities give them agility rarely surpassed in nature.

The challenge of robotic reproduction -- making of new robots by recombining two existing ones -- has been recently cracked and physically evolving robot systems have come within reach. Here we address the next big hurdle: producing an adequate brain for a newborn robot. In particular, we address the task of targeted locomotion which is arguably a fundamental skill in any practical implementation. We introduce a controller architecture and a generic learning method to allow a modular robot with an arbitrary shape to learn to walk towards a target and follow this target if it moves. Our approach is validated on three robots, a spider, a gecko, and their offspring, in three real-world scenarios.

The results of a routine check-up at Oregon Zoo in the US has caused a stir online when X-ray images of some of its animals were shared to Twitter. As part of the procedure the animals are photographed and scanned to ensure they are in good health. The eerie images reveal that the tail of a beaver has a bone reaching all the way to the tip and an X-ray of a snake reveals the mesmerising vertebrae that curve and stretch throughout the deadly ball python. Other images show the difference between birds (a screech owl) and flying mammals (a flying fox) and a hedgehog with trapped gas in its stomach. The Rodrigues flying fox (pictured) is actually a species of bat called Pteropus rodricensis and is only found in the wild on Rodrigues, an island in the Indian Ocean belonging to Mauritius.