Audio comprehension-including speech, non-speech sounds, and music-is essential for achieving human-level intelligence. Consequently, AI agents must demonstrate holistic audio understanding to qualify as generally intelligent. However, evaluating auditory intelligence comprehensively remains challenging. To address this gap, we introduce MMAU-Pro, the most comprehensive and rigorously curated benchmark for assessing audio intelligence in AI systems. MMAU-Pro contains 5,305 instances, where each instance has one or more audios paired with human expert-generated question-answer pairs, spanning speech, sound, music, and their combinations. Unlike existing benchmarks, MMAU-Pro evaluates auditory intelligence across 49 unique skills and multiple complex dimensions, including long-form audio comprehension, spatial audio reasoning, multi-audio understanding, among others. All questions are meticulously designed to require deliberate multi-hop reasoning, including both multiple-choice and open-ended response formats. Importantly, audio data is sourced directly ``from the wild" rather than from existing datasets with known distributions. We evaluate 22 leading open-source and proprietary multimodal AI models, revealing significant limitations: even state-of-the-art models such as Gemini 2.5 Flash and Audio Flamingo 3 achieve only 59.2% and 51.7% accuracy, respectively, approaching random performance in multiple categories. Our extensive analysis highlights specific shortcomings and provides novel insights, offering actionable perspectives for the community to enhance future AI systems' progression toward audio general intelligence. The benchmark and code is available at https://sonalkum.github.io/mmau-pro.

Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries.When descriptions specify fine-grained musical attributes such as tempo, key, chord progression, or rhythmic structure, existing models often fail to retrieve the correct audio.We show that this limitation stems from the contrastive learning objective itself: despite being trained on long captions, CLAP-based models effectively utilize only the first few tokens, discarding much of the information encoded in detailed prompts.Then, we propose FIGMA (FIne-Grained Music RetrievAl), a multi-view contrastive architecture that addresses this limitation by jointly optimizing global audio-text alignment and frame-level, token-wise alignment.This design enables FIGMA to capture both high-level semantic context and finegrained musical attributes within a unified representation space.Moreover, we formalize the task of Fine-Grained Music Retrieval and construct Fine-Grained Music Caption dataset (FGMCaps), a large-scale dataset of 380K music-caption pairs for training along with a 10K test set, both annotated with tempo, key, chord progression, beat count, as well as genre and mood.Extensive experiments demonstrate that FIGMA consistently outperforms existing CLAP-based music retrieval models across multiple music retrieval benchmarks, including out-of-domain evaluations, with relative improvements of up to 73.3%.

Ramaneswaran Selvakumar, Ashish Seth, Nishit Anand, Utkarsh Tyagi, Sonal Kumar, Sreyan Ghosh, Dinesh Manocha. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Ashish Seth, Utkarsh Tyagi, Ramaneswaran Selvakumar, Nishit Anand, Sonal Kumar, Sreyan Ghosh, Ramani Duraiswami, Chirag Agarwal, Dinesh Manocha. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Recent advancements in reasoning optimization have greatly enhanced the performance of large language models (LLMs). However, existing work fails to address the complexities of audio-visual scenarios, underscoring the need for further research. In this paper, we introduce AURELIA, a novel actor-critic based audio-visual (AV) reasoning framework that distills structured, step-by-step reasoning into AVLLMs at test time, improving their ability to process complex multi-modal inputs without additional training or fine-tuning. To further advance AVLLM reasoning skills, we present AVReasonBench, a challenging benchmark comprising 4500 audio-visual questions, each paired with detailed step-by-step reasoning. Our benchmark spans six distinct tasks, including AV-GeoIQ, which evaluates AV reasoning combined with geographical and cultural knowledge. Evaluating 18 AVLLMs on AVReasonBench reveals significant limitations in their multi-modal reasoning capabilities. Using AURELIA, we achieve up to a 100% relative improvement, demonstrating its effectiveness. This performance gain highlights the potential of reasoning-enhanced data generation for advancing AVLLMs in real-world applications. Our code and data will be publicly released at: https: //github.com/schowdhury671/aurelia.

Abstract Online social networks have grown exponentially in the recent years while finding applications in real life like marketing, recommendation systems, and social awareness campaigns. An important research area in this field is Influence Maximization, which pertains to finding methods for maximizing the spread of information (influence) across an OSN. Existing works in IM widely use a pre‐defined edge propagation probability for node activation. Hurst exponent (H), which depicts the self‐similarity in the time series depicting a user's past interaction behaviour, has also been used as activation criteria. In this work, we propose a Time Series Characteristic based Hurst‐based Diffusion Model (TSC‐HDM), which calculates H based on the stationary or non‐stationary characteristic of the time series. TSC‐HDM selects a handful of seed nodes and activates a seed node's inactive successor only if H > 0.5. The proposed model has been tested on four real‐world OSN datasets. The results have been compared against four other IM models – Independent Cascade, Weighted Cascade, Trivalency, and Hurst‐based Influence Maximization. TSC‐HDM is found to have achieved as much as 590% higher expected influence spread as compared to the other models. Moreover, TSC‐HDM has attained 344% better average influence spread than other state‐of‐the‐art models namely LIR, A‐Greedy, LPIMA, Genetic Algorithm with Dynamic Probabilities, NeighborsRemove, DegreeDecrease, IGIM, IRR, and PHG.