In this study, we investigate leveraging cross-attention control for efficient audio editing within auto-regressive models. Inspired by image editing methodologies, we develop a Prompt-to-Prompt-like approach that guides edits through cross and self-attention mechanisms. Integrating a diffusion-based strategy, influenced by Auffusion, we extend the model's functionality to support refinement edits, establishing a baseline for prompt-guided audio editing. Additionally, we introduce an alternative approach by incorporating MUSICGEN, a pre-trained frozen auto-regressive model, and propose three editing mechanisms, based on Replacement, Reweighting, and Refinement of the attention scores. We employ commonly-used music-specific evaluation metrics and a human study, to gauge time-varying controllability, adherence to global text cues, and overall audio realism. The automatic and human evaluations indicate that the proposed combination of prompt-to-prompt guidance with autoregressive generation models significantly outperforms the diffusion-based baseline in terms of melody, dynamics, and tempo of the generated audio. Our code is available at https://github.com/billsioros/EditGen

This paper presents our approach to EXIST 2025 Task 1, addressing text-based sexism detection in English and Spanish tweets through hierarchical Low-Rank Adaptation (LoRA) of Llama 3.1 8B. Our method introduces conditional adapter routing that explicitly models label dependencies across three hierarchically structured subtasks: binary sexism identification, source intention detection, and multilabel sexism categorization. Unlike conventional LoRA applications that target only attention layers, we apply adaptation to all linear transformations, enhancing the model's capacity to capture task-specific patterns. In contrast to complex data processing and ensemble approaches, we show that straightforward parameter-efficient fine-tuning achieves strong performance. We train separate LoRA adapters (rank=16, QLoRA 4-bit) for each subtask using unified multilingual training that leverages Llama 3.1's native bilingual capabilities. The method requires minimal preprocessing and uses standard supervised learning. Our multilingual training strategy eliminates the need for separate language-specific models, achieving 1.7-2.4\% F1 improvements through cross-lingual transfer. With only 1.67\% trainable parameters compared to full fine-tuning, our approach reduces training time by 75\% and model storage by 98\%, while achieving competitive performance across all subtasks (ICM-Hard: 0.6774 for binary classification, 0.4991 for intention detection, 0.6519 for multilabel categorization).

This paper presents a novel rule-based approach for generating music by varying existing tunes. We parse each tune to find the Pathway Assembly (PA) [ 1], that is a structure representing all repetitions in the tune. The Sequitur algorithm [2 ] is used for this. The result is a grammar. We then carry out mutation on the grammar, rather than on a tune directly. There are potentially 19 types of mutations such as adding, removing, swapping or reversing parts of the grammar that can be applied to the grammars. The system employs one of the mutations randomly in this step to automatically manipulate the grammar. Following the mutation, we need to expand the grammar which returns a new tune. The output after 1 or more mutations will be a new tune related to the original tune. Our study examines how tunes change gradually over the course of multiple mutations. Edit distances, structural complexity and length of the tunes are used to show how a tune is changed after multiple mutations. In addition, the size of effect of each mutation type is analyzed. As a final point, we review the musical aspect of the output tunes. It should be noted that the study only focused on generating new pitch sequences. The study is based on an Irish traditional tune dataset and a list of integers has been used to represent each tune's pitch values.

Manila, Philippines – When former Philippines President Rodrigo Duterte was arrested by the International Criminal Court (ICC) in March, Sheerah Escuerdo spoke to a local television station, welcoming the politician's detention on charges of murder linked to his war on drugs. Escuerdo, who lost her 18-year-old brother, Ephraim, to Duterte's war, clutched a portrait of her sibling during the interview with News 5 Everywhere as she demanded justice for his killing. Days later, she was shocked to find an AI-generated video of her slain brother circulating on Facebook, in which he said he was alive and accused his sister of lying. Are they paying you to do this?" the computer-generated image of Ephraim said. The video, posted online by a pro-Duterte influencer with 11,000 followers, immediately drew thousands of views on Facebook. One of the comments read, "Fake drug war victims". It was Escudero and her brother's image from her News 5 Everywhere interview that the influencer had used to ...

Sign up for the Slatest to get the most insightful analysis, criticism, and advice out there, delivered to your inbox daily. As a classically trained singer preparing for a professional career, Erin Perry can see quite clearly how artificial intelligence is upending her field--all the way down to the classroom. Perry just completed her first year as a graduate student in voice performance at the Peabody Institute, the prestigious music conservatory run by Johns Hopkins University. It's been rewarding so far: She's been learning how to navigate the modern classical music sector and confronting the relevant impacts of generative A.I., having taken on a project to study the major record labels' lawsuit against the Amazon-backed A.I. startup Anthropic, which trained its models on songwriters' lyrics sans permission or compensation. Understandably, Perry's rather skeptical of A.I.'s artistic applications, and fearful of the sweeping effects it could have on her chosen field, especially as generative-music startups like Suno and Udio are programmed to replicate specific artists and musical styles.

Although Large Language Models (LLMs) have demonstrated significant advancements in natural language processing tasks, their effectiveness in the classification and transformation of abusive text into non-abusive versions remains an area for exploration. In this study, we aim to use LLMs to transform abusive text (tweets and reviews) featuring hate speech and swear words into non-abusive text, while retaining the intent of the text. We evaluate the performance of two state-of-the-art LLMs, such as Gemini, GPT-4o, DeekSeek and Groq, on their ability to identify abusive text. We them to transform and obtain a text that is clean from abusive and inappropriate content but maintains a similar level of sentiment and semantics, i.e. the transformed text needs to maintain its message. Afterwards, we evaluate the raw and transformed datasets with sentiment analysis and semantic analysis. Our results show Groq provides vastly different results when compared with other LLMs. We have identified similarities between GPT-4o and DeepSeek-V3.

Function Calling is a crucial technique that enables Large Language Models (LLMs) to interact with external systems through APIs. However, the high latency associated with LLM-based Function Calling significantly impacts user experience. This paper presents a novel approach called Oriented Distillation for Inline Acceleration (ODIA) that leverages online user interaction data to accelerate Function Calling. By automatically identifying "simple queries" from production traffic and distilling knowledge from larger models to smaller ones, our method reduces response latency by 45% (expected) and 78% (median) while maintaining accuracy. We demonstrate the effectiveness of our approach through real-world deployment in a music application, where the smaller model successfully handles 60% of traffic with negligible accuracy loss. Our method requires minimal human intervention and continuously improves through automated data collection and model updating, making it a practical solution for production environments.

In the past year, Generative Recommendations (GRs) have undergone substantial advancements, especially in leveraging the powerful sequence modeling and reasoning capabilities of Large Language Models (LLMs) to enhance overall recommendation performance. LLM-based GRs are forming a new paradigm that is distinctly different from discriminative recommendations, showing strong potential to replace traditional recommendation systems heavily dependent on complex hand-crafted features. In this paper, we provide a comprehensive survey aimed at facilitating further research of LLM-based GRs. Initially, we outline the general preliminaries and application cases of LLM-based GRs. Subsequently, we introduce the main considerations when LLM-based GRs are applied in real industrial scenarios. Finally, we explore promising directions for LLM-based GRs. We hope that this survey contributes to the ongoing advancement of the GR domain.

Current Retrieval-Augmented Generation systems use uniform processing, causing inefficiency as simple queries consume resources similar to complex multi-hop tasks. We present SymRAG, a framework that introduces adaptive query routing via real-time complexity and load assessment to select symbolic, neural, or hybrid pathways. SymRAG's neuro-symbolic approach adjusts computational pathways based on both query characteristics and system load, enabling efficient resource allocation across diverse query types. By combining linguistic and structural query properties with system load metrics, SymRAG allocates resources proportional to reasoning requirements. Evaluated on 2,000 queries across HotpotQA (multi-hop reasoning) and DROP (discrete reasoning) using Llama-3.2-3B and Mistral-7B models, SymRAG achieves competitive accuracy (97.6--100.0% exact match) with efficient resource utilization (3.6--6.2% CPU utilization, 0.985--3.165s processing). Disabling adaptive routing increases processing time by 169--1151%, showing its significance for complex models. These results suggest adaptive computation strategies are more sustainable and scalable for hybrid AI systems that use dynamic routing and neuro-symbolic frameworks.

Language models often struggle with cross-mode knowledge retrieval -- the ability to access knowledge learned in one format (mode) when queried in another. We demonstrate that models trained on multiple data sources (e.g., Wikipedia and TinyStories) exhibit significantly reduced accuracy when retrieving knowledge in a format different from its original training mode. This paper quantitatively investigates this phenomenon through a controlled study of random token sequence memorization across different modes. We first explore dataset rewriting as a solution, revealing that effective cross-mode retrieval requires prohibitively extensive rewriting efforts that follow a sigmoid-like relationship. As an alternative, we propose CASCADE, a novel pretraining algorithm that uses cascading datasets with varying sequence lengths and computing losses on only the second half of each training sequence to capture knowledge at different scales. Our experiments demonstrate that CASCADE outperforms dataset rewriting approaches, even when compressed into a single model with a unified loss function. This work provides both qualitative evidence of cross-mode retrieval limitations and a practical solution to enhance language models' ability to access knowledge independently of its presentational format.