We introduce MAVERIX (Multimodal Audio-Visual Evaluation and Recognition IndeX), a unified benchmark to probe video understanding in multimodal LLMs, encompassing video, audio, and text inputs with human performance baselines. Although recent advancements in audiovisual models have shown substantial progress, the field lacks a standardized evaluation framework to thoroughly assess their cross-modality comprehension performance. MAVERIX curates 2,556 questions from 700 videos, in the form of both multiple-choice and open-ended formats, explicitly designed to evaluate multimodal models through questions that necessitate tight integration of video and audio information, spanning a broad spectrum of agentic scenarios. MAVERIX uniquely provides models with questions that closely mimic the multimodal understanding experiences available to humans during decision-making processes. To our knowledge, MAVERIX is the first benchmark aimed explicitly at assessing comprehensive audiovisual integration in such granularity. Experiments with state-of-the-art models, including Qwen 2.5 Omni and Gemini 2.5 Flash-Lite, show performance around 64% accuracy, while human experts reach near-ceiling performance of 92.8%, exposing a substantial gap to human-level comprehension. With standardized evaluation protocols, a rigorously annotated pipeline, and a public toolkit, MAVERIX establishes a challenging testbed for advancing audiovisual multimodal intelligence, with the website publicly available below.

Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully hand-crafted lexicons developed by experts. This poses a two-fold problem. Firstly, the lexicons are generated using a fixed phoneme set, usually, ARPABET or IPA, which might not be the most optimal way to represent phonemes for all languages. Secondly, the man-hours required to produce such an expert lexicon are very high. In this paper, we eliminate both of these issues by using recent advances in self-supervised learning to obtain data-driven phoneme representations instead of fixed representations. We compare our lexicon-free approach against strong baselines that utilize a well-crafted lexicon. Furthermore, we show that our data-driven lexicon-free method performs as good or even marginally better than the conventional rule-based or lexicon-based neural G2Ps in terms of Mean Opinion Score (MOS) while using no prior language lexicon or phoneme set, i.e. no linguistic expertise.

In spite of their huge success, transformer models remain difficult to scale in depth. In this work, we develop a unified signal propagation theory and provide formulae that govern the moments of the forward and backward signal through the transformer model. Our framework can be used to understand and mitigate vanishing/exploding gradients, rank collapse, and instability associated with high attention scores. We also propose DeepScaleLM, an initialization and scaling scheme that conserves unit output/gradient moments throughout the model, enabling the training of very deep models with 1000 layers. We find that transformer models could be much deeper - our deep models with fewer parameters outperform shallow models in Language Modeling, Speech Translation, and Image Classification, across encoder-only, decoder-only and encoder-decoder variants, for both Pre-LN and Post-LN transformers, for multiple datasets and model sizes. These improvements also translate into improved performance on downstream Question Answering tasks and improved robustness for Image Classification.

We consider the problem of correctly identifying the mode of a discrete distribution $\mathcal{P}$ with sufficiently high probability by observing a sequence of i.i.d. samples drawn from $\mathcal{P}$. This problem reduces to the estimation of a single parameter when $\mathcal{P}$ has a support set of size $K = 2$. After noting that this special case is handled very well by prior-posterior-ratio (PPR) martingale confidence sequences (Waudby-Smith and Ramdas, 2020), we propose a generalisation to mode estimation, in which $\mathcal{P}$ may take $K \geq 2$ values. To begin, we show that the "one-versus-one" principle to generalise from $K = 2$ to $K \geq 2$ classes is more efficient than the "one-versus-rest" alternative. We then prove that our resulting stopping rule, denoted PPR-1v1, is asymptotically optimal (as the mistake probability is taken to 0). PPR-1v1 is simple and computationally light, and incurs significantly fewer samples than competitors even in the non-asymptotic regime. We demonstrate its gains in two practical applications of sampling: election forecasting and verification of smart contracts in blockchains.

Ishan Tarunesh, Sushil Khyalia, Vishwajeet Kumar, Ganesh Ramakrishnan, Preethi Jyothi. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

Time series data are ubiquitous in real-world applications. However, one of the most common problems is that the time series could have missing values by the inherent nature of the data collection process. So imputing missing values from multivariate (correlated) time series is imperative to improve a prediction performance while making an accurate data-driven decision. Conventional works for imputation simply delete missing values or fill them based on mean/zero. Although recent works based on deep neural networks have shown remarkable results, they still have a limitation to capture the complex generation process of multivariate time series. In this paper, we propose a novel imputation method for multivariate time series, called STING (Self-attention based Time-series Imputation Networks using GAN). We take advantage of generative adversarial networks and bidirectional recurrent neural networks to learn the latent representations of time series. In addition, we introduce a novel attention mechanism to capture the weighted correlations of a whole sequence and avoid the potential bias brought by unrelated ones. The experimental results on three real-world datasets demonstrate that STING outperforms the existing state-of-the-art methods in terms of imputation accuracy as well as downstream tasks with the imputed values therein.