Multi-rotor Unmanned Aerial Vehicles (UAVs) need to tilt in order to move; this modifies the UAV's antenna orientation. We consider the scenario where a multi-rotor UAV serves as a communication relay between a Base Station (BS) and another UAV. We propose a framework to generate feasible trajectories for the multi-rotor UAV relay while considering its motion dynamics and the motion-induced changes of the antenna orientation. The UAV relay's trajectory is optimized to maximize the end-to-end number of bits transmitted. Numerical simulations in MATLAB and Gazebo show the benefits of accounting for the antenna orientation variations due to the UAV tilt.

Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale. They also, paradoxically, struggle with basic functionality, such as arithmetic or factual lookup, where much simpler and smaller models excel. In this paper, we show that LMs can teach themselves to use external tools via simple APIs and achieve the best of both worlds. We introduce Toolformer, a model trained to decide which APIs to call, when to call them, what arguments to pass, and how to best incorporate the results into future token prediction. This is done in a self-supervised way, requiring nothing more than a handful of demonstrations for each API. We incorporate a range of tools, including a calculator, a Q\&A system, two different search engines, a translation system, and a calendar. Toolformer achieves substantially improved zero-shot performance across a variety of downstream tasks, often competitive with much larger models, without sacrificing its core language modeling abilities.

Specialised pre-trained language models are becoming more frequent in NLP since they can potentially outperform models trained on generic texts. BioBERT (Sanh et al., 2019) and BioClinicalBERT (Alsentzer et al., 2019) are two examples of such models that have shown promise in medical NLP tasks. Many of these models are overparametrised and resource-intensive, but thanks to techniques like Knowledge Distillation (KD), it is possible to create smaller versions that perform almost as well as their larger counterparts. In this work, we specifically focus on development of compact language models for processing clinical texts (i.e. We developed a number of efficient lightweight clinical transformers using knowledge distillation and continual learning, with the number of parameters ranging from 15 million to 65 million. These models performed comparably to larger models such as BioBERT and ClinicalBioBERT and significantly outperformed other compact models trained on general or biomedical data. Our extensive evaluation was done across several standard datasets and covered a wide range of clinical text-mining tasks, including Natural Language Inference, Relation Extraction, Named Entity Recognition, and Sequence Classification. To our knowledge, this is the first comprehensive study specifically focused on creating efficient and compact transformers for clinical NLP tasks. The models and code used in this study can be found on our Huggingface profile at https: //huggingface.co/nlpie and Github page at https://github.com/ Large language models pre-trained on generic texts serve as the foundation upon which most stateof-the-art NLP models are built. There is ample evidence that, for certain domains and downstream tasks, models that are pre-trained on specialised data outperform baselines that have only relied on generic texts (Sanh et al., 2019; Alsentzer et al., 2019; Beltagy et al., 2019; Nguyen et al., 2020; Chalkidis et al., 2020).

Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques like adapters and sparse fine-tuning have been developed. Adapters are modular, as they can be combined to adapt a model towards different facets of knowledge (e.g., dedicated language and/or task adapters). Sparse fine-tuning is expressive, as it controls the behavior of all model components. In this work, we introduce a new fine-tuning method with both these desirable properties. In particular, we learn sparse, real-valued masks based on a simple variant of the Lottery Ticket Hypothesis. Task-specific masks are obtained from annotated data in a source language, and language-specific masks from masked language modeling in a target language. Both these masks can then be composed with the pretrained model. Unlike adapter-based fine-tuning, this method neither increases the number of parameters at inference time nor alters the original model architecture. Most importantly, it outperforms adapters in zero-shot cross-lingual transfer by a large margin in a series of multilingual benchmarks, including Universal Dependencies, MasakhaNER, and AmericasNLI. Based on an in-depth analysis, we additionally find that sparsity is crucial to prevent both 1) interference between the fine-tunings to be composed and 2) overfitting. We release the code and models at https://github.com/cambridgeltl/composable-sft.

Mixed-precision quantization mostly predetermines the model bit-width settings before actual training due to the non-differential bit-width sampling process, obtaining sub-optimal performance. Worse still, the conventional static quality-consistent training setting, i.e., all data is assumed to be of the same quality across training and inference, overlooks data quality changes in real-world applications which may lead to poor robustness of the quantized models. In this paper, we propose a novel Data Quality-aware Mixed-precision Quantization framework, dubbed DQMQ, to dynamically adapt quantization bit-widths to different data qualities. The adaption is based on a bit-width decision policy that can be learned jointly with the quantization training. Concretely, DQMQ is modeled as a hybrid reinforcement learning (RL) task that combines model-based policy optimization with supervised quantization training. By relaxing the discrete bit-width sampling to a continuous probability distribution that is encoded with few learnable parameters, DQMQ is differentiable and can be directly optimized end-to-end with a hybrid optimization target considering both task performance and quantization benefits. Trained on mixed-quality image datasets, DQMQ can implicitly select the most proper bit-width for each layer when facing uneven input qualities. Extensive experiments on various benchmark datasets and networks demonstrate the superiority of DQMQ against existing fixed/mixed-precision quantization methods.

The 37th AAAI Conference on Artificial Intelligence (AAAI2023) started on Tuesday 7 February and runs until Tuesday 14 February. Here, we found out what participants have been up to during the first couple of days, and look ahead to some of the events planned for the rest of week. Speakers and attendees from all over the world convened in Washington D.C. yesterday for a whole week of artificial intelligence demonstration and discussion. Thank you for your contributions to the design and implementation of organ exchanges. Thank you for your contributions to the field of #AI.

The release of toxic gases by industries, emissions from vehicles, and an increase in the concentration of harmful gases and particulate matter in the atmosphere are all contributing factors to the deterioration of the quality of the air. Factors such as industries, urbanization, population growth, and the increased use of vehicles contribute to the rapid increase in pollution levels, which can adversely impact human health. This paper presents a model for forecasting the air quality index in Nigeria using the Bi-directional LSTM model. The air pollution data was downloaded from an online database (UCL). The dataset was pre-processed using both pandas tools in python. The pre-processed result was used as input features in training a Bi-LSTM model in making future forecasts of the values of the particulate matter Pm2.5, and Pm10. The Bi-LSTM model was evaluated using some evaluation parameters such as mean square error, mean absolute error, absolute mean square, and R^2 square. The result of the Bi-LSTM shows a mean square error of 52.99%, relative mean square error of 7.28%, mean absolute error of 3.4%, and R^2 square of 97%. The model. This shows that the model follows a seamless trend in forecasting the air quality in Port Harcourt, Nigeria.

Understanding the halo-galaxy connection is fundamental in order to improve our knowledge on the nature and properties of dark matter. In this work we build a model that infers the mass of a halo given the positions, velocities, stellar masses, and radii of the galaxies it hosts. In order to capture information from correlations among galaxy properties and their phase-space, we use Graph Neural Networks (GNNs), that are designed to work with irregular and sparse data. We train our models on galaxies from more than 2,000 state-of-the-art simulations from the Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) project. Our model, that accounts for cosmological and astrophysical uncertainties, is able to constrain the masses of the halos with a $\sim$0.2 dex accuracy. Furthermore, a GNN trained on a suite of simulations is able to preserve part of its accuracy when tested on simulations run with a different code that utilizes a distinct subgrid physics model, showing the robustness of our method. The PyTorch Geometric implementation of the GNN is publicly available on Github at https://github.com/PabloVD/HaloGraphNet

(Dis)agreement detection aims to identify the authors' attitudes or positions (\textit{{agree, disagree, neutral}}) towards a specific text. It is limited for existing methods merely using textual information for identifying (dis)agreements, especially for cross-domain settings. Social relation information can play an assistant role in the (dis)agreement task besides textual information. We propose a novel method to extract such relation information from (dis)agreement data into an inductive social relation graph, merely using the comment-reply pairs without any additional platform-specific information. The inductive social relation globally considers the historical discussion and the relation between authors. Textual information based on a pre-trained language model and social relation information encoded by pre-trained RGCN are jointly considered for (dis)agreement detection. Experimental results show that our model achieves state-of-the-art performance for both the in-domain and cross-domain tasks on the benchmark -- DEBAGREEMENT. We find social relations can boost the performance of the (dis)agreement detection model, especially for the long-token comment-reply pairs, demonstrating the effectiveness of the social relation graph. We also explore the effect of the knowledge graph embedding methods, the information fusing method, and the time interval in constructing the social relation graph, which shows the effectiveness of our model.

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training tasks is the key component in making stronger MT LMs. In this work, we report an unexpected finding that an expert LM fine-tuned on just a single task can outperform an MT LM trained with 300+ different tasks on 11 different unseen datasets and on 13 datasets of the BIG-bench benchmark by a mean accuracy of 3.20% and 1.29%, respectively. This finding casts doubt on the previously held belief that simply scaling the number of tasks makes stronger MT LMs. Leveraging this finding, we further show that this distributed approach of training a separate expert LM per training task instead of a single MT LM for zero-shot inference possesses many benefits including (1) avoiding negative task transfer that often occurs during instruction tuning, (2) being able to continually learn new tasks without having to re-train on previous tasks to avoid catastrophic forgetting, and (3) showing compositional capabilities when merging individual experts together. The code is available at https://github.com/joeljang/ELM.