Alignment of Large Language Models (LLMs) remains an unsolved problem. Human preferences are highly distributed and can be captured at multiple levels of abstraction, from the individual to diverse populations. Organisational preferences, represented by standards and principles, are defined to mitigate reputational risk or meet legislative obligations. In this paper, we present ABC Align, a novel alignment methodology for LLMs that enables integration of the standards and preferences of a large media organisation into the LLM itself. We combine a set of data and methods that build on recent breakthroughs in synthetic data generation, preference optimisation, and post-training model quantisation. Our unified approach mitigates bias and improves accuracy, while preserving reasoning capability, as measured against standard benchmarks.

The non-profit settlement sector in Canada supports newcomers in achieving successful integration. This sector faces increasing operational pressures amidst rising immigration targets, which highlights a need for enhanced efficiency and innovation, potentially through reliable AI solutions. The ad-hoc use of general-purpose generative AI, such as ChatGPT, might become a common practice among newcomers and service providers to address this need. However, these tools are not tailored for the settlement domain and can have detrimental implications for immigrants and refugees. We explore the risks that these tools might pose on newcomers to first, warn against the unguarded use of generative AI, and second, to incentivize further research and development in creating AI literacy programs as well as customized LLMs that are aligned with the preferences of the impacted communities. Crucially, such technologies should be designed to integrate seamlessly into the existing workflow of the settlement sector, ensuring human oversight, trustworthiness, and accountability.

In the Western music tradition, chords are the main constituent components of harmony, a fundamental dimension of music. Despite its relevance for several Music Information Retrieval (MIR) tasks, chord-annotated audio datasets are limited and need more diversity. One way to improve those resources is to leverage the large number of chord annotations available online, but this requires aligning them with music audio. However, existing audio-to-score alignment techniques, which typically rely on Dynamic Time Warping (DTW), fail to address this challenge, as they require weakly aligned data for precise synchronisation. In this paper, we introduce ChordSync, a novel conformer-based model designed to seamlessly align chord annotations with audio, eliminating the need for weak alignment. We also provide a pre-trained model and a user-friendly library, enabling users to synchronise chord annotations with audio tracks effortlessly. In this way, ChordSync creates opportunities for harnessing crowd-sourced chord data for MIR, especially in audio chord estimation, thereby facilitating the generation of novel datasets. Additionally, our system extends its utility to music education, enhancing music learning experiences by providing accurately aligned annotations, thus enabling learners to engage in synchronised musical practices.

Gaussian process (GP) models have received increasingly attentions in recent years due to their superb prediction accuracy and modeling flexibility. To address the computational burdens of GP models for large-scale datasets, distributed learning for GPs are often adopted. Current aggregation models for distributed GPs are not time-efficient when incorporating correlations between GP experts. In this work, we propose a novel approach for aggregated prediction in distributed GPs. The technique is suitable for both the exact and sparse variational GPs. The proposed method incorporates correlations among experts, leading to better prediction accuracy with manageable computational requirements. As demonstrated by empirical studies, the proposed approach results in more stable predictions in less time than state-of-the-art consistent aggregation models.

We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. Our model is a simple transformer architecture with streaming memory for real-time video processing. SAM 2 trained on our data provides strong performance across a wide range of tasks. In video segmentation, we observe better accuracy, using 3x fewer interactions than prior approaches. In image segmentation, our model is more accurate and 6x faster than the Segment Anything Model (SAM). We believe that our data, model, and insights will serve as a significant milestone for video segmentation and related perception tasks. We are releasing a version of our model, the dataset and an interactive demo.

Rebuses are puzzles requiring constrained multi-step reasoning to identify a hidden phrase from a set of images and letters. In this work, we introduce a large collection of verbalized rebuses for the Italian language and use it to assess the rebus-solving capabilities of state-of-the-art large language models. While general-purpose systems such as LLaMA-3 and GPT-4o perform poorly on this task, ad-hoc fine-tuning seems to improve models' performance. However, we find that performance gains from training are largely motivated by memorization. Our results suggest that rebus solving remains a challenging test bed to evaluate large language models' linguistic proficiency and sequential instruction-following skills.

Large language models (LLMs) bear great potential for automating tedious development tasks such as creating and maintaining code documentation. However, it is unclear to what extent developers can effectively prompt LLMs to create concise and useful documentation. We report on a controlled experiment with 20 professionals and 30 computer science students tasked with code documentation generation for two Python functions. The experimental group freely entered ad-hoc prompts in a ChatGPT-like extension of Visual Studio Code, while the control group executed a predefined few-shot prompt. Our results reveal that professionals and students were unaware of or unable to apply prompt engineering techniques. Especially students perceived the documentation produced from ad-hoc prompts as significantly less readable, less concise, and less helpful than documentation from prepared prompts. Some professionals produced higher quality documentation by just including the keyword Docstring in their ad-hoc prompts. While students desired more support in formulating prompts, professionals appreciated the flexibility of ad-hoc prompting. Participants in both groups rarely assessed the output as perfect. Instead, they understood the tools as support to iteratively refine the documentation. Further research is needed to understand which prompting skills and preferences developers have and which support they need for certain tasks.

We explore the hypothesis that poor compositional generalization in neural networks is caused by difficulties with learning effective routing. To solve this problem, we propose the concept of block-operations, which is based on splitting all activation tensors in the network into uniformly sized blocks and using an inductive bias to encourage modular routing and modification of these blocks. Based on this concept we introduce the Multiplexer, a new architectural component that enhances the Feed Forward Neural Network (FNN). We experimentally confirm that Multiplexers exhibit strong compositional generalization. On both a synthetic and a realistic task our model was able to learn the underlying process behind the task, whereas both FNNs and Transformers were only able to learn heuristic approximations. We propose as future work to use the principles of block-operations to improve other existing architectures.

In recent years, Generative Artificial Intelligence (GenAI) has undergone a profound transformation in addressing intricate tasks involving diverse modalities such as textual, auditory, visual, and pictorial generation. Within this spectrum, text-to-image (TTI) models have emerged as a formidable approach to generating varied and aesthetically appealing compositions, spanning applications from artistic creation to realistic facial synthesis, and demonstrating significant advancements in computer vision, image processing, and multimodal tasks. The advent of Latent Diffusion Models (LDMs) signifies a paradigm shift in the domain of AI capabilities. This article delves into the feasibility of employing the Stable Diffusion LDM to illustrate literary works. For this exploration, seven classic Brazilian books have been selected as case studies. The objective is to ascertain the practicality of this endeavor and to evaluate the potential of Stable Diffusion in producing illustrations that augment and enrich the reader's experience. We will outline the beneficial aspects, such as the capacity to generate distinctive and contextually pertinent images, as well as the drawbacks, including any shortcomings in faithfully capturing the essence of intricate literary depictions. Through this study, we aim to provide a comprehensive assessment of the viability and efficacy of utilizing AI-generated illustrations in literary contexts, elucidating both the prospects and challenges encountered in this pioneering application of technology.

Some companies(e.g., Microsoft Research and Google DeepMind) have discovered some of the limitations of GPTs autoregressive paradigm next-word prediction, manifested in the model lack of planning, working memory, backtracking, and reasoning skills. GPTs rely on a local and greedy process of generating the next word, without a global understanding of the task or the output.We have confirmed the above limitations through specialized empirical studies of code comprehension. Although GPT4 is good at producing fluent and coherent text, it cannot handle complex logic and generate new code that haven not been seen, and it relies too much on the formatting of the prompt to generate the correct code.We propose a new paradigm for code understanding that goes beyond the next-word prediction paradigm, inspired by the successful application of diffusion techniques to image generation(Dalle2, Sora) and protein structure generation(AlphaFold3), which have no autoregressive constraints.Instead of encoding the code in a form that mimics natural language, we encode the code as a heterogeneous image paradigm with a memory of global information that mimics both images and protein structures.We then refer to Sora's CLIP upstream text-to-image encoder model to design a text-to-code encoder model that can be applied to various downstream code understanding tasks.The model learns the global understanding of code under the new paradigm heterogeneous image, connects the encoding space of text and code, and encodes the input of text into the vector of code most similar to it.Using self-supervised comparative learning on 456,360 text-code pairs, the model achieved a zero-shot prediction of new data. This work is the basis for future work on code generation using diffusion techniques under a new paradigm to avoid autoregressive limitations.