Explore the vast range of titles available.

The anthropometric parameters (body mass index [BMI], waist circumference [WC], and skinfold thickness), fasting blood glucose (FBG), and blood pressure were recorded. The study demonstrated high prevalence of intra-abdominal (16.5%) and subcutaneous adiposity (27%). [...]about 17% of the population having abdominal obesity as measured by several parameters in the present study is of important concern since it is associated with metabolic and cardiovascular disorders.11,8,91 The high percentage of subjects who had MetS in the whole group was 5.5% also notable. [...]for estimation of BMR, we used the predictive equations not with the help of indirect calorimetry. Menon S, Venugopal R. A comparative study of lipid profile, body mass index, and waist circumference among Type 2 diabetes mellitus patients with poor and good metabolic control and normal age-matched control group.

The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs). In this work, we investigate an approach that leverages the strengths of Large Language Models (LLMs) and image generation models to create synthetic image-text pairs for efficient and effective VLM training. Our method employs a pretrained text-to-image model to synthesize image embeddings from captions generated by an LLM. Despite the text-to-image model and VLM initially being trained on the same data, our approach leverages the image generator's ability to create novel compositions, resulting in synthetic image embeddings that expand beyond the limitations of the original dataset. Extensive experiments demonstrate that our VLM, finetuned on synthetic data achieves comparable performance to models trained solely on human-annotated data, while requiring significantly less data. Furthermore, we perform a set of analyses on captions which reveals that semantic diversity and balance are key aspects for better downstream performance. Finally, we show that synthesizing images in the image embedding space is 25\\% faster than in the pixel space. We believe our work not only addresses a significant challenge in VLM training but also opens up promising avenues for the development of self-improving multi-modal models.

Power-law scaling indicates that large-scale training with uniform sampling is prohibitively slow. Active learning methods aim to increase data efficiency by prioritizing learning on the most relevant examples. Despite their appeal, these methods have yet to be widely adopted since no one algorithm has been shown to a) generalize across models and tasks b) scale to large datasets and c) yield overall FLOP savings when accounting for the overhead of data selection. In this work we propose a method which satisfies these three properties, leveraging small, cheap proxy models to estimate \"learnability\" scores for datapoints, which are used to prioritize data for the training of much larger models. As a result, our models require 46% and 51% fewer training updates and up to 25% less total computation to reach the same performance as uniformly trained visual classifiers on JFT and multimodal models on ALIGN. Finally, we find our data-prioritization scheme to be complementary with recent data-curation and learning objectives, yielding a new state-of-the-art in several multimodal transfer tasks.

Understanding long, real-world videos requires modeling of long-range visual dependencies. To this end, we explore video-first architectures, building on the common paradigm of transferring large-scale, image--text models to video via shallow temporal fusion. However, we expose two limitations to the approach: (1) decreased spatial capabilities, likely due to poor video--language alignment in standard video datasets, and (2) higher memory consumption, bottlenecking the number of frames that can be processed. To mitigate the memory bottleneck, we systematically analyze the memory/accuracy trade-off of various efficient methods: factorized attention, parameter-efficient image-to-video adaptation, input masking, and multi-resolution patchification. Surprisingly, simply masking large portions of the video (up to 75%) during contrastive pre-training proves to be one of the most robust ways to scale encoders to videos up to 4.3 minutes at 1 FPS. Our simple approach for training long video-to-text models, which scales to 1B parameters, does not add new architectural complexity and is able to outperform the popular paradigm of using much larger LLMs as an information aggregator over segment-based information on benchmarks with long-range temporal dependencies (YouCook2, EgoSchema).

We propose `Tapestry', a novel approach to pooled testing with application to COVID-19 testing with quantitative Reverse Transcription Polymerase Chain Reaction (RT-PCR) that can result in shorter testing time and conservation of reagents and testing kits. Tapestry combines ideas from compressed sensing and combinatorial group testing with a novel noise model for RT-PCR used for generation of synthetic data. Unlike Boolean group testing algorithms, the input is a quantitative readout from each test and the output is a list of viral loads for each sample relative to the pool with the highest viral load. While other pooling techniques require a second confirmatory assay, Tapestry obtains individual sample-level results in a single round of testing, at clinically acceptable false positive or false negative rates. We also propose designs for pooling matrices that facilitate good prediction of the infected samples while remaining practically viable. When testing \\(n\\) samples out of which \\(k \\ll n\\) are infected, our method needs only \\(O(k \\log n)\\) tests when using random binary pooling matrices, with high probability. However, we also use deterministic binary pooling matrices based on combinatorial design ideas of Kirkman Triple Systems to balance between good reconstruction properties and matrix sparsity for ease of pooling. In practice, we have observed the need for fewer tests with such matrices than with random pooling matrices. This makes Tapestry capable of very large savings at low prevalence rates, while simultaneously remaining viable even at prevalence rates as high as 9.5\\%. Empirically we find that single-round Tapestry pooling improves over two-round Dorfman pooling by almost a factor of 2 in the number of tests required. We validate Tapestry in simulations and wet lab experiments with oligomers in quantitative RT-PCR assays. Lastly, we describe use-case scenarios for deployment.

While recent benchmarks have spurred a lot of new work on improving the generalization of pretrained multilingual language models on multilingual tasks, techniques to improve code-switched natural language understanding tasks have been far less explored. In this work, we propose the use of bilingual intermediate pretraining as a reliable technique to derive large and consistent performance gains on three different NLP tasks using code-switched text. We achieve substantial absolute improvements of 7.87%, 20.15%, and 10.99%, on the mean accuracies and F1 scores over previous state-of-the-art systems for Hindi-English Natural Language Inference (NLI), Question Answering (QA) tasks, and Spanish-English Sentiment Analysis (SA) respectively. We show consistent performance gains on four different code-switched language-pairs (Hindi-English, Spanish-English, Tamil-English and Malayalam-English) for SA. We also present a code-switched masked language modelling (MLM) pretraining technique that consistently benefits SA compared to standard MLM pretraining using real code-switched text.

We introduce T5Gemma 2, the next generation of the T5Gemma family of lightweight open encoder-decoder models, featuring strong multilingual, multimodal and long-context capabilities. T5Gemma 2 follows the adaptation recipe (via UL2) in T5Gemma -- adapting a pretrained decoder-only model into an encoder-decoder model, and extends it from text-only regime to multimodal based on the Gemma 3 models. We further propose two methods to improve the efficiency: tied word embedding that shares all embeddings across encoder and decoder, and merged attention that unifies decoder self- and cross-attention into a single joint module. Experiments demonstrate the generality of the adaptation strategy over architectures and modalities as well as the unique strength of the encoder-decoder architecture on long context modeling. Similar to T5Gemma, T5Gemma 2 yields comparable or better pretraining performance and significantly improved post-training performance than its Gemma 3 counterpart. We release the pretrained models (270M-270M, 1B-1B and 4B-4B) to the community for future research.

Stateless model checking (SMC) is one of the standard approaches to the verification of concurrent programs. As scheduling non-determinism creates exponentially large spaces of thread interleavings, SMC attempts to partition this space into equivalence classes and explore only a few representatives from each class. The efficiency of this approach depends on two factors: (a) the coarseness of the partitioning, and (b) the time to generate representatives in each class. For this reason, the search for coarse partitionings that are efficiently explorable is an active research challenge. In this work we present RVF-SMC, a new SMC algorithm that uses a novel \\emph{reads-value-from (RVF)} partitioning. Intuitively, two interleavings are deemed equivalent if they agree on the value obtained in each read event, and read events induce consistent causal orderings between them. The RVF partitioning is provably coarser than recent approaches based on Mazurkiewicz and \"reads-from\" partitionings. Our experimental evaluation reveals that RVF is quite often a very effective equivalence, as the underlying partitioning is exponentially coarser than other approaches. Moreover, RVF-SMC generates representatives very efficiently, as the reduction in the partitioning is often met with significant speed-ups in the model checking task.

The discovery of the lazy neuron phenomenon in trained Transformers, where the vast majority of neurons in their feed-forward networks (FFN) are inactive for each token, has spurred tremendous interests in activation sparsity for enhancing large model efficiency. While notable progress has been made in translating such sparsity to wall-time benefits, modern Transformers have moved away from the ReLU activation function crucial to this phenomenon. Existing efforts on re-introducing activation sparsity often degrade model quality, increase parameter count, complicate or slow down training. Sparse attention, the application of sparse activation to the attention mechanism, often faces similar challenges. This paper introduces the Spark Transformer, a novel architecture that achieves a high level of activation sparsity in both FFN and the attention mechanism while maintaining model quality, parameter count, and standard training procedures. Our method realizes sparsity via top-k masking for explicit control over sparsity level. Crucially, we introduce statistical top-k, a hardware-accelerator-friendly, linear-time approximate algorithm that avoids costly sorting and mitigates significant training slowdown from standard top-\\(k\\) operators. Furthermore, Spark Transformer reallocates existing FFN parameters and attention key embeddings to form a low-cost predictor for identifying activated entries. This design not only mitigates quality loss from enforced sparsity, but also enhances wall-time benefit. Pretrained with the Gemma-2 recipe, Spark Transformer demonstrates competitive performance on standard benchmarks while exhibiting significant sparsity: only 8% of FFN neurons are activated, and each token attends to a maximum of 256 tokens. This sparsity translates to a 2.5x reduction in FLOPs, leading to decoding wall-time speedups of up to 1.79x on CPU and 1.40x on GPU.

Understanding long, real-world videos requires modeling of long-range visual dependencies. To this end, we explore video-first architectures, building on the common paradigm of transferring large-scale, image--text models to video via shallow temporal fusion. However, we expose two limitations to the approach: (1) decreased spatial capabilities, likely due to poor video--language alignment in standard video datasets, and (2) higher memory consumption, bottlenecking the number of frames that can be processed. To mitigate the memory bottleneck, we systematically analyze the memory/accuracy trade-off of various efficient methods: factorized attention, parameter-efficient image-to-video adaptation, input masking, and multi-resolution patchification. Surprisingly, simply masking large portions of the video (up to 75%) during contrastive pre-training proves to be one of the most robust ways to scale encoders to videos up to 4.3 minutes at 1 FPS. Our simple approach for training long video-to-text models, which scales to 1B parameters, does not add new architectural complexity and is able to outperform the popular paradigm of using much larger LLMs as an information aggregator over segment-based information on benchmarks with long-range temporal dependencies (YouCook2, EgoSchema).