Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and collaborative filtering. Following the convention of RS, existing practices exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called \textit{Diversity-Promoting Collaborative Metric Learning} (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to introduce a set of multiple representations for each user in the system where users' preference toward an item is aggregated by taking the minimum item-user distance among their embedding set. Specifically, we instantiate two effective assignment strategies to explore a proper quantity of vectors for each user. Meanwhile, a \textit{Diversity Control Regularization Scheme} (DCRS) is developed to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could induce a smaller generalization error than traditional CML. Furthermore, we notice that CML-based approaches usually require \textit{negative sampling} to reduce the heavy computational burden caused by the pairwise objective therein. In this paper, we reveal the fundamental limitation of the widely adopted hard-aware sampling from the One-Way Partial AUC (OPAUC) perspective and then develop an effective sampling alternative for the CML-based paradigm. Finally, comprehensive experiments over a range of benchmark datasets speak to the efficacy of DPCML. Code are available at \url{https://github.com/statusrank/LibCML}.

Large language models (LLMs) have shown success in generating high-quality responses. In order to achieve better alignment with LLMs with human preference, various works are proposed based on specific optimization process, which, however, is not suitable to Black-Box LLMs like GPT-4, due to inaccessible parameters. In Black-Box LLMs case, their performance is highly dependent on the quality of the provided prompts. Existing methods to enhance response quality often involve a prompt refinement model, yet these approaches potentially suffer from semantic inconsistencies between the refined and original prompts, and typically overlook the relationship between them. To address these challenges, we introduce a self-instructed in-context learning framework that empowers LLMs to deliver more effective responses by generating reliable derived prompts to construct informative contextual environments. Our approach incorporates a self-instructed reinforcement learning mechanism, enabling direct interaction with the response model during derived prompt generation for better alignment. We then formulate querying as an in-context learning task, using responses from LLMs combined with the derived prompts to establish a contextual demonstration for the original prompt. This strategy ensures alignment with the original query, reduces discrepancies from refined prompts, and maximizes the LLMs' in-context learning capability. Extensive experiments demonstrate that the proposed method not only generates more reliable derived prompts but also significantly enhances LLMs' ability to deliver more effective responses, including Black-Box models such as GPT-4.

This paper introduces VoxHakka, a text-to-speech (TTS) system designed for Taiwanese Hakka, a critically under-resourced language spoken in Taiwan. Leveraging the YourTTS framework, VoxHakka achieves high naturalness and accuracy and low real-time factor in speech synthesis while supporting six distinct Hakka dialects. This is achieved by training the model with dialect-specific data, allowing for the generation of speaker-aware Hakka speech. To address the scarcity of publicly available Hakka speech corpora, we employed a cost-effective approach utilizing a web scraping pipeline coupled with automatic speech recognition (ASR)-based data cleaning techniques. This process ensured the acquisition of a high-quality, multi-speaker, multi-dialect dataset suitable for TTS training. Subjective listening tests conducted using comparative mean opinion scores (CMOS) demonstrate that VoxHakka significantly outperforms existing publicly available Hakka TTS systems in terms of pronunciation accuracy, tone correctness, and overall naturalness. This work represents a significant advancement in Hakka language technology and provides a valuable resource for language preservation and revitalization efforts.

We propose a novel symbolic music representation and Generative Adversarial Network (GAN) framework specially designed for symbolic multitrack music generation. The main theme of symbolic music generation primarily encompasses the preprocessing of music data and the implementation of a deep learning framework. Current techniques dedicated to symbolic music generation generally encounter two significant challenges: training data's lack of information about chords and scales and the requirement of specially designed model architecture adapted to the unique format of symbolic music representation. In this paper, we solve the above problems by introducing new symbolic music representation with MusicLang chord analysis model. We propose our MMT-BERT architecture adapting to the representation. To build a robust multitrack music generator, we fine-tune a pre-trained MusicBERT model to serve as the discriminator, and incorporate relativistic standard loss. This approach, supported by the in-depth understanding of symbolic music encoded within MusicBERT, fortifies the consonance and humanity of music generated by our method. Experimental results demonstrate the effectiveness of our approach which strictly follows the state-of-the-art methods.

Unsupervised heterogeneous graph representation learning (UHGRL) has gained increasing attention due to its significance in handling practical graphs without labels. However, heterophily has been largely ignored, despite its ubiquitous presence in real-world heterogeneous graphs. In this paper, we define semantic heterophily and propose an innovative framework called Latent Graphs Guided Unsupervised Representation Learning (LatGRL) to handle this problem. First, we develop a similarity mining method that couples global structures and attributes, enabling the construction of fine-grained homophilic and heterophilic latent graphs to guide the representation learning. Moreover, we propose an adaptive dual-frequency semantic fusion mechanism to address the problem of node-level semantic heterophily. To cope with the massive scale of real-world data, we further design a scalable implementation. Extensive experiments on benchmark datasets validate the effectiveness and efficiency of our proposed framework. The source code and datasets have been made available at https://github.com/zxlearningdeep/LatGRL.

This project aimed to develop an automated cinematography platform using an unmanned aerial vehicle. Quadcopters are a great platform for shooting aerial scenes but are difficult to maneuver smoothly and can require expertise to pilot. We aim to design an algorithm to enable automated cinematography of a desired object of interest. Given the location of an object and other obstacles in the environment, the drone is able to plan its trajectory while simultaneously keeping the desired object in the video frame and avoiding obstacles. The high maneuverability of quadcopter platforms coupled with the desire for smooth movement and stability from camera platforms means a robust motion planning algorithm must be developed which can take advantage of the quadcopter's abilities while creating motion paths which satisfy the ultimate goal of capturing aerial video. This project aims to research, develop, simulate, and test such an algorithm.

Not everything on the internet is true. This unfortunate fact requires both humans and models to perform complex reasoning about credibility when working with retrieved information. In NLP, this problem has seen little attention. Indeed, retrieval-augmented models are not typically expected to distrust retrieved documents. Human experts overcome the challenge by gathering signals about the context, reliability, and tendency of source documents - that is, they perform source criticism. We propose a novel NLP task focused on finding and summarising such signals. We introduce a new dataset of 6,709 "media background checks" derived from Media Bias / Fact Check, a volunteer-run website documenting media bias. We test open-source and closed-source LLM baselines with and without retrieval on this dataset, finding that retrieval greatly improves performance. We furthermore carry out human evaluation, demonstrating that 1) media background checks are helpful for humans, and 2) media background checks are helpful for retrieval-augmented models.

Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability. However, real function-calling data is quite challenging to collect and annotate, while synthetic data generated by existing pipelines tends to lack coverage and accuracy. In this paper, we present ToolACE, an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data. ToolACE leverages a novel self-evolution synthesis process to curate a comprehensive API pool of 26,507 diverse APIs. Dialogs are further generated through the interplay among multiple agents, guided by a formalized thinking process. To ensure data accuracy, we implement a dual-layer verification system combining rule-based and model-based checks. We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard, rivaling the latest GPT-4 models. Our model and a subset of the data are publicly available at https://huggingface.co/Team-ACE.

If this week's rumor about a video game set in the universe of 2022's The Batman got your hopes up, I have some bad news: no such thing is in development at the moment. Responding to a question on Threads about whether Warner Bros. has a game in the works based on the Robert Pattinson-led film, DC Studios' co-head James Gunn said, "Sadly there is no truth to this whatsoever." The rumor stems from a Puck report that was published on Friday. The Batman, directed by Matt Reeves, popped back up in theaters on Wednesday as part of AMC's celebration of the 85th anniversary of Batman. Work on a sequel is currently underway, and an HBO limited series focusing on The Penguin is slated to come out this fall.

Years before Star Wars, video game designers had begun to explore galactic dogfighting. In 1962, Spacewar!, the first formal computer game, was a rudimentary but influential attempt: two narrow triangles swirled around the gravity well of a star, launching torpedoes at each other. Having established the medium's first principles, hundreds of developers attempted to refine and perfect the genre, which rose and dived in fashion but never fully warped away. Cygni is, perhaps, the highest production attempt yet, a debut from a tiny Scottish studio that answers the improbable question: what if Steven Spielberg had directed Space Invaders? Stylistically reminiscent of the polarity-swapping arcade classic Ikaruga, Cygni is a technological masterclass, your spaceship sweeping over distant robot battlefields, buffeted in the blast of a thousand fireworks.