This paper explores the influence of Italian high school students' proficiency in mathematics and the Italian language on their university enrolment choices, specifically focusing on STEM (Science, Technology, Engineering, and Mathematics) courses. We distinguish between students from scientific and humanistic backgrounds in high school, providing valuable insights into their enrolment preferences. Furthermore, we investigate potential gender differences in response to similar previous educational choices and achievements. The study employs gradient boosting methodology, known for its high predicting performance and ability to capture non-linear relationships within data, and adjusts for variables related to the socio-demographic characteristics of the students and their previous educational achievements. Our analysis reveals significant differences in the enrolment choices based on previous high school achievements. The findings shed light on the complex interplay of academic proficiency, gender, and high school background in shaping students' choices regarding university education, with implications for educational policy and future research endeavours.

Traditional deep learning often overlooks bytes, the basic units of the digital world, where all forms of information and operations are encoded and manipulated in binary format. Inspired by the success of next token prediction in natural language processing, we introduce bGPT, a model with next byte prediction to simulate the digital world. bGPT matches specialized models in performance across various modalities, including text, audio, and images, and offers new possibilities for predicting, simulating, and diagnosing algorithm or hardware behaviour. It has almost flawlessly replicated the process of converting symbolic music data, achieving a low error rate of 0.0011 bits per byte in converting ABC notation to MIDI format. In addition, bGPT demonstrates exceptional capabilities in simulating CPU behaviour, with an accuracy exceeding 99.99% in executing various operations. Leveraging next byte prediction, models like bGPT can directly learn from vast binary data, effectively simulating the intricate patterns of the digital world.

As highly automated vehicles reach higher deployment rates, they find themselves in increasingly dangerous situations. Knowing that the consequence of a crash is significant for the health of occupants, bystanders, and properties, as well as to the viability of autonomy and adjacent businesses, we must search for more efficacious ways to comprehensively and reliably train autonomous vehicles to better navigate the complex scenarios with which they struggle. We therefore introduce a taxonomy of potentially adversarial elements that may contribute to poor performance or system failures as a means of identifying and elucidating lesser-seen risks. This taxonomy may be used to characterize failures of automation, as well as to support simulation and real-world training efforts by providing a more comprehensive classification system for events resulting in disengagement, collision, or other negative consequences. This taxonomy is created from and tested against real collision events to ensure comprehensive coverage with minimal class overlap and few omissions. It is intended to be used both for the identification of harm-contributing adversarial events and in the generation thereof (to create extreme edge- and corner-case scenarios) in training procedures.

The Argentinian real estate market presents a unique case study characterized by its unstable and rapidly shifting macroeconomic circumstances over the past decades. Despite the existence of a few datasets for price prediction, there is a lack of mixed modality datasets specifically focused on Argentina. In this paper, the first edition of ARED is introduced. A comprehensive real estate price prediction dataset series, designed for the Argentinian market. This edition contains information solely for Jan-Feb 2024. It was found that despite the short time range captured by this zeroth edition (44 days), time dependent phenomena has been occurring mostly on a market level (market as a whole). Nevertheless future editions of this dataset, will most likely contain historical data. Each listing in ARED comprises descriptive features, and variable-length sets of images.

This paper investigates the use of large language models (LLMs) for extracting sample lists of polymer nanocomposites (PNCs) from full-length materials science research papers. The challenge lies in the complex nature of PNC samples, which have numerous attributes scattered throughout the text. The complexity of annotating detailed information on PNCs limits the availability of data, making conventional document-level relation extraction techniques impractical due to the challenge in creating comprehensive named entity span annotations. To address this, we introduce a new benchmark and an evaluation technique for this task and explore different prompting strategies in a zero-shot manner. We also incorporate self-consistency to improve the performance. Our findings show that even advanced LLMs struggle to extract all of the samples from an article. Finally, we analyze the errors encountered in this process, categorizing them into three main challenges, and discuss potential strategies for future research to overcome them.

In this paper, we develop upon the topic of loss function learning, an emergent meta-learning paradigm that aims to learn loss functions that significantly improve the performance of the models trained under them. Specifically, we propose a new meta-learning framework for task and model-agnostic loss function learning via a hybrid search approach. The framework first uses genetic programming to find a set of symbolic loss functions. Second, the set of learned loss functions is subsequently parameterized and optimized via unrolled differentiation. The versatility and performance of the proposed framework are empirically validated on a diverse set of supervised learning tasks. Results show that the learned loss functions bring improved convergence, sample efficiency, and inference performance on tabulated, computer vision, and natural language processing problems, using a variety of task-specific neural network architectures.

Recent years have witnessed a significant increase in the performance of Vision and Language tasks. Foundational Vision-Language Models (VLMs), such as CLIP, have been leveraged in multiple settings and demonstrated remarkable performance across several tasks. Such models excel at object-centric recognition yet learn text representations that seem invariant to word order, failing to compose known concepts in novel ways. However, no evidence exists that any VLM, including large-scale single-stream models such as GPT-4V, identifies compositions successfully. In this paper, we introduce a framework to significantly improve the ability of existing models to encode compositional language, with over 10% absolute improvement on compositionality benchmarks, while maintaining or improving the performance on standard object-recognition and retrieval benchmarks. Our code and pre-trained models are publicly available at https://github.com/netflix/clove.

Iterative combinatorial auctions are widely used in high stakes settings such as spectrum auctions. Such auctions can be hard to understand analytically, making it difficult for bidders to determine how to behave and for designers to optimize auction rules to ensure desirable outcomes such as high revenue or welfare. In this paper, we investigate whether multi-agent reinforcement learning (MARL) algorithms can be used to understand iterative combinatorial auctions, given that these algorithms have recently shown empirical success in several other domains. We find that MARL can indeed benefit auction analysis, but that deploying it effectively is nontrivial. We begin by describing modelling decisions that keep the resulting game tractable without sacrificing important features such as imperfect information or asymmetry between bidders. We also discuss how to navigate pitfalls of various MARL algorithms, how to overcome challenges in verifying convergence, and how to generate and interpret multiple equilibria. We illustrate the promise of our resulting approach by using it to evaluate a specific rule change to a clock auction, finding substantially different auction outcomes due to complex changes in bidders' behavior.

In this paper we present PeLLE, a family of large language models based on the RoBERTa architecture, for Brazilian Portuguese, trained on curated, open data from the Carolina corpus. Aiming at reproducible results, we describe details of the pretraining of the models. We also evaluate PeLLE models against a set of existing multilingual and PT-BR refined pretrained Transformer-based LLM encoders, contrasting performance of large versus smaller-but-curated pretrained models in several downstream tasks. We conclude that several tasks perform better with larger models, but some tasks benefit from smaller-but-curated data in its pretraining.

As the usage of large language models (LLMs) grows, performing efficient inference with these models becomes increasingly important. While speculative decoding has recently emerged as a promising direction for speeding up inference, existing methods are limited in their ability to scale to larger speculation budgets, and adapt to different hyperparameters and hardware. This paper introduces Sequoia, a scalable, robust, and hardware-aware algorithm for speculative decoding. To attain better scalability, Sequoia introduces a dynamic programming algorithm to find the optimal tree structure for the speculated tokens. To achieve robust speculative performance, Sequoia uses a novel sampling and verification method that outperforms prior work across different decoding temperatures. Finally, Sequoia introduces a hardware-aware tree optimizer that maximizes speculative performance by automatically selecting the token tree size and depth for a given hardware platform. Evaluation shows that Sequoia improves the decoding speed of Llama2-7B, Llama2-13B, and Vicuna-33B on an A100 by up to $4.04\times$, $3.73\times$, and $2.27\times$. For offloading setting on L40, Sequoia achieves as low as 0.56 s/token for exact Llama2-70B inference latency, which is $9.96\times$ on our optimized offloading system (5.6 s/token), $9.7\times$ than DeepSpeed-Zero-Inference, $19.5\times$ than Huggingface Accelerate.